# S^3martCirc: Self-supervised Smart Circuit Discovery

arXiv: https://arxiv.org/abs/2609.00755 · HTML: https://mlsanity.com/paper/2609.00755/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Circuits and mechanistic analysis, one of 13 directions in Mechanistic interpretability.
- Builds on 19 of its 28 references that are in the map.
- First posted on arXiv 1 Sep 2026.

## Placed in

- Mechanistic interpretability / [Circuits and mechanistic analysis](https://mlsanity.com/mechinterp/circuits-and-mechanistic-analysis/)

## Builds on (most cited first, 19 of 19)

- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [Progress measures for grokking via mechanistic interpretability](https://mlsanity.com/paper/2301.05217/) (2023)
- [How to use and interpret activation patching](https://mlsanity.com/paper/2404.15255/) (2024)
- [Attribution Patching Outperforms Automated Circuit Discovery](https://mlsanity.com/paper/2310.10348/) (2023)
- [Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms](https://mlsanity.com/paper/2403.17806/) (2024)
- [Circuit Component Reuse Across Tasks in Transformer Language Models](https://mlsanity.com/paper/2310.08744/) (2023)
- [Can ChatGPT Replace Traditional KBQA Models? An In-depth Analysis of the Question Answering Performance of the GPT LLM Family](https://mlsanity.com/paper/2303.07992/) (2023)
- [Finding Transformer Circuits with Edge Pruning](https://mlsanity.com/paper/2406.16778/) (2024)
- [Probing BERT in Hyperbolic Spaces](https://mlsanity.com/paper/2104.03869/) (2021)
- [TEaR: Improving LLM-based Machine Translation with Systematic Self-Refinement](https://mlsanity.com/paper/2402.16379/) (2024)
- [Same Task, Different Circuits: Disentangling Modality-Specific Mechanisms in VLMs](https://mlsanity.com/paper/2506.09047/) (2025)
- [SAIF: A Sparse Autoencoder Framework for Interpreting and Steering Instruction Following of Language Models](https://mlsanity.com/paper/2502.11356/) (2025)
- [Black-box Uncertainty Quantification Method for LLM-as-a-Judge](https://mlsanity.com/paper/2410.11594/) (2024)
- [Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective](https://mlsanity.com/paper/2506.05166/) (2025)
- [How does GPT-2 Predict Acronyms? Extracting and Understanding a Circuit via Mechanistic Interpretability](https://mlsanity.com/paper/2405.04156/) (2024)
- [Detecting and Understanding Vulnerabilities in Language Models via Mechanistic Interpretability](https://mlsanity.com/paper/2407.19842/) (2024)
- [Beyond the Black Box: Interpretability of LLMs in Finance](https://mlsanity.com/paper/2505.24650/) (2025)
- [Science Across Languages: Assessing LLM Multilingual Translation of Scientific Papers](https://mlsanity.com/paper/2502.17882/) (2025)

## Abstract (arXiv)

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.