S^3martCirc: Self-supervised Smart Circuit Discovery

Large Language Models (LLMs) have demonstrated remarkable performance across diverse tasks, from text summarization to question answering. Despite these capabilities, their black-box nature obscures internal decision-making processes. Mechanistic interpretability (MI) aims to address this by reverse-engineering neural networks into human-understandable algorithms. Current MI approaches for LLMs typically follow a two-stage paradigm: first identifying important components (circuit discovery), where components are typically individual nodes such as an attention head or feedforward neuron, and second determining the role they play in a certain task (functional interpretation). However, this sequential approach overlooks a fundamental insight: a component's importance and its functional role are inherently codependent. Unifying these stages presents two key challenges: (1) functional roles are often tied to specific nodes or components, limiting generalization, and (2) their identification relies on subjective interpretation rather than quantifiable metrics. To address these challenges, we propose S^3martCirc (Self-supervised Smart Circuit Discovery), a unified framework that simultaneously discovers circuits and interprets functionality. S^3martCirc abstracts node behavior into two general computational roles that generalize across tasks and defines a quantitative metric for assigning them, enabling importance and functional role to be discovered jointly rather than in sequence. Extensive experiments show that our framework outperforms existing methods in circuit discovery.

Circuit Fine-Tuning for Compute-Efficient Transformer Adaptation

Parameter-Efficient Fine-Tuning (PEFT) has become the de facto standard for adapting Vision Transformers (ViTs) to downstream tasks. While parameter count has been the dominant efficiency metric in PEFT, it does not imply \textit{compute efficiency}: parameter-sparse methods can still incur full-model training cost per step, and typically need long schedules to reach peak accuracy. We introduce Circuit Fine-Tuning (CFT), a compute-efficient framework that uses circuit discovery---conventionally used to explain trained models---to select modules for fine-tuning before training. Whereas attribution is conventionally formulated against a trained task head, we formulate it against a near-zero-initialized probe head, which isolates the response of the backbone to the target distribution rather than the preferences of a particular classifier. CFT then fine-tunes only the recovered subgraph. CFT needs no learning-rate warmup and reaches peak accuracy in ${\sim}20$ epochs on average---versus $44$--$96$ for strong PEFT baselines---yielding $2.3$--$6.6\times$ fewer training FLOPs and up to $16\times$ less wall-clock time, while adding zero parameters and no inference operations. Experiments across a standard visual transfer benchmark (VTAB-1k), hierarchical backbones (Swin), domain-shifted medical imaging (CBIS-DDSM), and a vision-language model (Gemma-3 on CUB-200) demonstrate the effectiveness of CFT. Code is available at https://github.com/UriKialy/CFT

Where Animacy Lives in Large Language Models: Tracing the Circuits of the Animacy Concept

Distinguishing animate from inanimate concepts in written language requires more than shallow text processing, as it involves recognizing complex selectional constraints and contextual cues, such as verb-argument interactions. Yet, current large language models (LLMs) appear to be capable of doing it. We investigate whether this animacy-sensitive behavior of LLMs can be traced to a localized set of causally relevant components and connections. To do so, we construct a controlled dataset of minimal pairs and perform circuit discovery on four open-weight models. Through in-depth experiments and ablations, we show that a causal mechanism responsible for handling animacy in these models does exist, thus discovering an animacy circuit. At the same time, this circuit appears to be less localized compared to other known ones and generalizes only partially across models and animacy tasks, confirming the distributed, context-dependent, and somewhat graded nature of the animacy concept.

Demystifying Variance in Circuit Discovery of LLMs

Circuit discovery is a key technique in mechanistic interpretability to pinpoint the model components that are crucial for performing a given task. Although the current state-of-the-art method (EAP-IG) performs well on the metric of (un)faithfulness, it suffers from substantial variability. This includes resampling variance, where the circuit changes when we probe with a new batch of data from the same distribution; rephrasing variance, where the discovered circuit shifts when the prompts are rephrased; and sample-wise variance, where a circuit with low population unfaithfulness exhibits large fluctuations in unfaithfulness across individual samples. This paper studies the roots of these variances. We demonstrate that CEAP, our new circuit discovery method that improves upon EAP-IG with a theoretical guarantee, can substantially lessen resampling variance. We further show that rephrasing variance arises because prompts with different templates tend to activate different circuits in the model. This leads us to argue that it may be challenging to find a comprehensive circuit that explains and controls the model's behavior on a task, which can be expressed in countless templates, suggesting that LLMs may be inherently hard to steer. We show that sparsity, which has been claimed to form more compact and interpretable task circuits, fails to solve this problem. Regarding sample-wise variance, we argue that it is largely benign: extremely poor unfaithfulness scores often stem from how unfaithfulness is defined, rather than from defects in the measured circuits. We show that the magnitude of unfaithfulness is affected by selective contribution scaling, a neural mechanism that accounts for the extremely poor scores sometimes observed.

Circuit Tracing in Autoregressive Protein Language Models

Protein language models (pLMs) can generate novel protein sequences with properties beyond those observed in nature, yet the mechanisms underlying protein generation remain poorly understood. Existing mechanistic interpretability methods based on sparse autoencoders and transcoders primarily focus on protein representation learning models and do not capture the computation required for autoregressive generation. Here, we introduce ProGenMech, a mechanistic interpretability framework for generative protein language models that extends cross-layer transcoders (CLTs) to ProGen3, a sparse Mixture-of-Experts model trained for both causal generation and span infilling. Unlike per-layer approaches, CLTs reconstruct each layer using sparse latent variables from all preceding layers, enabling faithful recovery of inter-layer generative computation. We further develop a zero-shot circuit discovery framework to identify sparse latent circuits responsible for protein generation and fitness prediction. In causal generation and zero-shot fitness estimation tasks, ProGenMech outperforms local transcoder baselines in recovering ProGen3's probability distribution and functional scoring behavior, while matching the original model's generative distribution in span infilling tasks. Moreover, the recovered circuits reveal biologically meaningful motifs and functional regions associated with conserved sequence patterns and protein fitness landscapes, establishing a foundation for interpretable and steerable protein generation.

Closure-Validated Circuit Discovery in Attention Heads: Co-activation Proposes, Ablation Disposes

Interpretability increasingly treats groups of components, not individual units, as the basic object, and proposes to find them by clustering co-activation statistics. We ask whether such a cheap signal actually identifies an attention-head circuit. Adapting a sparse-autoencoder clustering recipe to attention heads -- but validating by causal ablation rather than reconstruction -- we cluster heads and then run a closure test: ablate the discovered community and compare per-example damage to matched-random controls. Across two dense 1B-scale models (Pythia 1B, OLMo 1B) and two input distributions, the communities pass closure. In a Mixture-of-Experts model (OLMoE-1B-7B), route-conditional clustering recovers a statistically real signal that nonetheless does not survive closure -- ablation improves loss, the wrong direction. Extending closure across training, attention-target selectivity and participation ratio decouple from function in both directions. We conclude that a cheap signal is a circuit proposal, not a confirmed circuit; closure is what separates them.

How Many Counterfactuals Does It Take? Probing VLM Hallucinations Through Circuits and Causal Effects

Visual Language Models (VLMs) are known to produce hallucinated predictions that are not grounded in visual evidence, yet existing approaches lack a principled understanding of how robust such predictions are under counterfactual perturbations. In this work, we study the sample complexity of counterfactual robustness for hallucinated outputs in VLMs. We define a causal influence metric based on log-probability differences between factual, counterfactual, and activation-patched runs, and use it to characterize the stability of hallucinated predictions. By leveraging circuit discovery techniques (CD-T), we identify model components responsible for these predictions and track their activation differences across counterfactual samples. We then derive empirical bounds on the minimum number of counterfactual samples m required to reliably detect instability in hallucinated outputs, using concentration inequalities and variance estimates of the causal influence distribution.

When Attribution Patching Lies: Diagnosis and a Second-Order Correction

A central goal of mechanistic interpretability is to identify which internal components causally drive a language model's behavior. Because these importance estimates serve as the evidence for identifying circuits, systematic errors can lead to the misidentification of the underlying mechanisms. While activation patching provides a gold-standard causal metric, its computational cost is prohibitive at scale. Practitioners instead rely on attribution patching, a gradient-based, first-order approximation whose reliability remains poorly understood. In this work, we characterize the source of this unreliability, demonstrating that the dominant error stems from the non-linearities in the downstream network rather than local curvature at the patched component. This insight yields three practical tools: (i) a reliability score to detect untrustworthy estimates, (ii) error bounds quantifying potential attribution mis-specifications, and (iii) a Hessian-vector-product (HVP) correction that eliminates the leading-order error with only one additional backward pass. In evaluations across five model families (124M-9B parameters) and both random-token and naturalistic (name-swap) perturbations, HVP is the only second-order correction feasible at larger scale, where standard baselines like Integrated Gradients become computationally prohibitive. In comparative experiments, a multi-step HVP variant matches or exceeds the accuracy of Integrated Gradients at significantly lower compute, outperforming prior second-order baselines. These improvements lead to higher-fidelity circuit recovery on standard benchmarks and support a Screen-Flag-Fix workflow that targets computational effort only toward the components flagged as unreliable.

Many Circuits, One Mechanism: Input Variation and Evaluation Granularity in Circuit Discovery

Circuit discovery methods identify subgraphs that explain model behaviors, and structural differences between discovered circuits are commonly interpreted as evidence of distinct mechanisms. We test this assumption by varying input-token frequency while holding the task fixed. The discovered circuits appear specialized by frequency when compared structurally, but functional and representational analyses show no reliable evidence of corresponding differences. We term this mismatch phantom specialization. Using the Literal Sequence Copying task across four frequency bands plus a frequency-weighted control, we extract 75 circuits from five Pythia models (70M-1.4B). We find that structurally distinct circuits implement the same computation: band-specific edges transfer broadly across bands, a core shared across most bands recovers at least 99% of circuit performance in models above 70M, and causal interchange interventions confirm that internal representations are interchangeable across frequency bands. A smaller subject-verb agreement replication shows the same pattern: circuits differ structurally but transfer broadly across bands, and the core shared by most bands recovers nearly all circuit accuracy. Repeated extractions within the same band further suggest that discovery algorithms sample from an equivalence class of valid subgraphs rather than recovering a unique mechanism. Standard evaluation practice obscures this pattern: source-level evaluation inflates apparent faithfulness, while edge-level evaluation reveals the many-to-one mapping from structure to function. We do not test specialization at the level of token positions or features inside a component. Our results show that structural differences between circuits are not sufficient evidence for distinct mechanisms, and that exposing this requires edge-level evaluation and cross-condition transfer tests.