S^3martCirc: Self-supervised Smart Circuit Discovery

• URL: http://arxiv.org/abs/2609.00755v1
• Date: Tue, 01 Sep 2026 05:37:42 GMT
• Title: S^3martCirc: Self-supervised Smart Circuit Discovery
• Abstract summary: Large Language Models (LLMs) have demonstrated remarkable performance across diverse tasks.<n>Despite these capabilities, their black-box nature obscures internal decision-making processes.<n>Mechanistic interpretability aims to address this by reverse-engineering neural networks into human-understandable algorithms.
• Score: 44.37905543632994
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Issues with Measuring Task Complexity via Random Policies in Robotic Tasks [0.005771104869225669]
  Key challenge inReinforcement learning (RL) is measuring task complexity.<n>Few metrics exist for assessing task complexity in non-tabular domains.
  arXiv  Detail & Related papers  (2026-02-21T14:38:02Z)
• Cognitive Mirrors: Exploring the Diverse Functional Roles of Attention Heads in LLM Reasoning [54.12174882424842]
  Large language models (LLMs) have achieved state-of-the-art performance in a variety of tasks, but remain largely opaque in terms of their internal mechanisms.<n>We propose a novel interpretability framework to systematically analyze the roles and behaviors of attention heads.
  arXiv  Detail & Related papers  (2025-12-03T10:24:34Z)
• Selection, Reflection and Self-Refinement: Revisit Reasoning Tasks via a Causal Lens [19.316594303998667]
  Reasoning tasks have long been regarded as rigorous benchmarks for assessing the capabilities of machine learning models.<n>We revisit reasoning tasks from a causal perspective, seeking to understand their behavior in latent space.<n>We introduce a framework, called SR$2$, that incorporates the estimated latent variables as feedback into the selection mechanism.
  arXiv  Detail & Related papers  (2025-10-09T13:45:31Z)
• From Indirect Object Identification to Syllogisms: Exploring Binary Mechanisms in Transformer Circuits [5.1877231178075425]
  We investigate the ability of GPT-2 small to handle binary truth values by analyzing its behavior with syllogistic prompts.<n>Through our analysis of several syllogism tasks of varying difficulty, we identify multiple circuits that mechanistically explain GPT-2's logical-reasoning capabilities.
  arXiv  Detail & Related papers  (2025-08-22T05:54:11Z)
• EgoPrompt: Prompt Learning for Egocentric Action Recognition [49.12318087940015]
  EgoPrompt is a prompt learning-based framework to conduct egocentric action recognition task.<n>EgoPrompt achieves state-of-the-art performance across within-dataset, cross-dataset, and base-to-novel generalization benchmarks.
  arXiv  Detail & Related papers  (2025-08-05T09:47:07Z)
• Contextualize-then-Aggregate: Circuits for In-Context Learning in Gemma-2 2B [51.74607395697567]
  In-Context Learning (ICL) is an intriguing ability of large language models (LLMs)<n>We use causal interventions to identify information flow in Gemma-2 2B for five naturalistic ICL tasks.<n>We find that the model infers task information using a two-step strategy we call contextualize-then-aggregate.
  arXiv  Detail & Related papers  (2025-03-31T18:33:55Z)
• Benchmarking and Understanding Compositional Relational Reasoning of LLMs [1.915591735124465]
  We first propose a new synthetic benchmark called Generalized Associative Recall (GAR)<n> Evaluation shows that GAR is challenging enough for existing LLMs, revealing their fundamental deficiency in CRR.<n>We then use attribution patching to discover the core circuits reused by Vicuna-33B across different tasks and a set of vital attention heads.
  arXiv  Detail & Related papers  (2024-12-17T12:10:38Z)
• Adaptive Circuit Behavior and Generalization in Mechanistic Interpretability [3.138731415322007]
  We investigate the generality of the indirect object identification (IOI) circuit in GPT-2 small.<n>Our findings reveal that the circuit generalizes surprisingly well, reusing all of its components and mechanisms while only adding additional input edges.
  arXiv  Detail & Related papers  (2024-11-25T05:32:34Z)
• Compositional Attention: Disentangling Search and Retrieval [66.7108739597771]
  Multi-head, key-value attention is the backbone of the Transformer model and its variants. Standard attention heads learn a rigid mapping between search and retrieval. We propose a novel attention mechanism, called Compositional Attention, that replaces the standard head structure.
  arXiv  Detail & Related papers  (2021-10-18T15:47:38Z)
• Distribution Matching for Heterogeneous Multi-Task Learning: a Large-scale Face Study [75.42182503265056]
  Multi-Task Learning has emerged as a methodology in which multiple tasks are jointly learned by a shared learning algorithm. We deal with heterogeneous MTL, simultaneously addressing detection, classification & regression problems. We build FaceBehaviorNet, the first framework for large-scale face analysis, by jointly learning all facial behavior tasks.
  arXiv  Detail & Related papers  (2021-05-08T22:26:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.