# Position-aware Automatic Circuit Discovery

arXiv: https://arxiv.org/abs/2502.04577 · HTML: https://mlsanity.com/paper/2502.04577/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in Circuits and mechanistic analysis, one of 13 directions in Mechanistic interpretability.
- Builds on 17 of its 53 references that are in the map.
- First posted on arXiv 7 Feb 2025.

## Placed in

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

## Builds on (most cited first, 17 of 17)

- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small](https://mlsanity.com/paper/2211.00593/) (2022)
- [Attention is not Explanation](https://mlsanity.com/paper/1902.10186/) (2019)
- [Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models](https://mlsanity.com/paper/2403.19647/) (2024)
- [Causal Abstractions of Neural Networks](https://mlsanity.com/paper/2106.02997/) (2021)
- [Direct and Indirect Effects](https://mlsanity.com/paper/1301.2300/) (2013)
- [Attribution Patching Outperforms Automated Circuit Discovery](https://mlsanity.com/paper/2310.10348/) (2023)
- [A Survey of the State of Explainable AI for Natural Language Processing](https://mlsanity.com/paper/2010.00711/) (2020)
- [Localizing Model Behavior with Path Patching](https://mlsanity.com/paper/2304.05969/) (2023)
- [Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking](https://mlsanity.com/paper/2402.14811/) (2024)
- [Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms](https://mlsanity.com/paper/2403.17806/) (2024)
- [Causal Analysis of Syntactic Agreement Mechanisms in Neural Language Models](https://mlsanity.com/paper/2106.06087/) (2021)
- [Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing](https://mlsanity.com/paper/2102.12060/) (2021)
- [AtP*: An efficient and scalable method for localizing LLM behaviour to components](https://mlsanity.com/paper/2403.00745/) (2024)
- [FIND: A Function Description Benchmark for Evaluating Interpretability Methods](https://mlsanity.com/paper/2309.03886/) (2023)
- [Automatically Identifying Local and Global Circuits with Linear Computation Graphs](https://mlsanity.com/paper/2405.13868/) (2024)

## Built on by (most cited first, 14 of 14)

- [Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models](https://mlsanity.com/paper/2601.14004/) (2026)
- [Formal Mechanistic Interpretability: Automated Circuit Discovery with Provable Guarantees](https://mlsanity.com/paper/2602.16823/) (2026)
- [Rethinking Circuit Completeness in Language Models: AND, OR, and ADDER Gates](https://mlsanity.com/paper/2505.10039/) (2025)
- [Interpreting Attention Heads for Image-to-Text Information Flow in Large Vision-Language Models](https://mlsanity.com/paper/2509.17588/) (2025)
- [Decomposing Representation Space into Interpretable Subspaces with Unsupervised Learning](https://mlsanity.com/paper/2508.01916/) (2025)
- [Interpretability Can Be Actionable](https://mlsanity.com/paper/2605.11161/) (2026)
- [Start Making Sense(s): A Developmental Probe of Attention Specialization Using Lexical Ambiguity](https://mlsanity.com/paper/2511.21974/) (2025)
- [Large Language Models Generate Harmful Responses Using a Distinct Mechanism, Shared Across Harm Types](https://mlsanity.com/paper/2604.09544/) (2026)
- [Pitfalls in Evaluating Interpretability Agents](https://mlsanity.com/paper/2603.20101/) (2026)
- [TextTIGER: Text-based Intelligent Generation with Entity Prompt Refinement for Text-to-Image Generation](https://mlsanity.com/paper/2504.18269/) (2025)
- [Judge Circuits Explain Format-Induced Inconsistency in LLM-as-a-Judge](https://mlsanity.com/paper/2605.16023/) (2026)
- [Triangulation as an Acceptance Rule for Multilingual Mechanistic Interpretability](https://mlsanity.com/paper/2512.24842/) (2025)
- [CircuitKIT : Circuit Discovery, Evaluation, and Application Toolkit for Mechanistic Interpretability](https://mlsanity.com/paper/2607.19317/) (2026)
- [Circuit Condensation: Post-Training that Concentrates a Behavior's Causal Circuit](https://mlsanity.com/paper/2608.27254/) (2026)

## Abstract (arXiv)

A widely used strategy to discover and understand language model mechanisms is circuit analysis. A circuit is a minimal subgraph of a model's computation graph that executes a specific task. We identify a gap in existing circuit discovery methods: they assume circuits are position-invariant, treating model components as equally relevant across input positions. This limits their ability to capture cross-positional interactions or mechanisms that vary across positions. To address this gap, we propose two improvements to incorporate positionality into circuits, even on tasks containing variable-length examples. First, we extend edge attribution patching, a gradient-based method for circuit discovery, to differentiate between token positions. Second, we introduce the concept of a dataset schema, which defines token spans with similar semantics across examples, enabling position-aware circuit discovery in datasets with variable length examples. We additionally develop an automated pipeline for schema generation and application using large language models. Our approach enables fully automated discovery of position-sensitive circuits, yielding better trade-offs between circuit size and faithfulness compared to prior work.