# Circuits and mechanistic analysis

Area: [Mechanistic interpretability](https://mlsanity.com/mechinterp/index.md). HTML: https://mlsanity.com/mechinterp/circuits-and-mechanistic-analysis/

## Key facts

- Circuits and mechanistic analysis: 272 papers on arXiv since 2022 (data through 14 Oct 2026).
- 148 of its 272 mapped papers (54%) cite “Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small” (2022, arXiv 2211.00593).
- 128 of its 272 mapped papers (47%) cite “Towards Automated Circuit Discovery for Mechanistic Interpretability” (2023, arXiv 2304.14997).
- 10 new papers 24 Sep–14 Oct.

## Most cited here

- [Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small](https://mlsanity.com/paper/2211.00593/) (2022), cited by 148 papers here
- [Towards Automated Circuit Discovery for Mechanistic Interpretability](https://mlsanity.com/paper/2304.14997/) (2023), cited by 128 papers here
- [Progress measures for grokking via mechanistic interpretability](https://mlsanity.com/paper/2301.05217/) (2023), cited by 68 papers here
- [Attribution Patching Outperforms Automated Circuit Discovery](https://mlsanity.com/paper/2310.10348/) (2023), cited by 63 papers here
- [Mechanistic Interpretability for AI Safety -- A Review](https://mlsanity.com/paper/2404.14082/) (2024), cited by 29 papers here
- [Transcoders Find Interpretable LLM Feature Circuits](https://mlsanity.com/paper/2406.11944/) (2024), cited by 28 papers here
- [Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability](https://mlsanity.com/paper/2301.04709/) (2023), cited by 26 papers here
- [A Toy Model of Universality: Reverse Engineering How Networks Learn Group Operations](https://mlsanity.com/paper/2302.03025/) (2023), cited by 24 papers here
- [Open Problems in Mechanistic Interpretability](https://mlsanity.com/paper/2501.16496/) (2025), cited by 22 papers here
- [MIB: A Mechanistic Interpretability Benchmark](https://mlsanity.com/paper/2504.13151/) (2025), cited by 20 papers here

## New (24 Sep–14 Oct)

- [Interpreting Language Model Parameters](https://mlsanity.com/paper/2610.20748/) (2026-10-14)
- [The Ball and the Box: Two Geometries of Computation in Superposition](https://mlsanity.com/paper/2610.11744/) (2026-10-08)
- [CircuitTree: Composing Circuits into A Syllable Transcriber](https://mlsanity.com/paper/2610.12520/) (2026-10-07)
- [Slaying the Hydra: Interaction-Aware Circuit Discovery in Language Models](https://mlsanity.com/paper/2610.04017/) (2026-10-02)
- [Certified Mechanistic Edits: Behavioral Guarantees for Skill Removal and Preservation](https://mlsanity.com/paper/2610.03502/) (2026-10-02)
- [Are We Recovering Mechanisms? Objective-Level Recovery Gaps in Mechanistic Interpretability](https://mlsanity.com/paper/2610.02098/) (2026-10-01)
- [When Models Don't Manipulate Manifolds: The Geometry of a Comparison Task](https://mlsanity.com/paper/2609.37680/) (2026-09-29)
- [Rethinking Circuit Evaluation: Do Circuits Explain Model Errors?](https://mlsanity.com/paper/2609.35686/) (2026-09-28)
- [Representational Simplicity and Circuit Size Dissociate in a Threshold-Dependent Way: A Controlled Test via Adversarial Training](https://mlsanity.com/paper/2609.35890/) (2026-09-27)
- [Mechanistic Interpretability Reveals Shared Causal Subspaces in Brain-to-Speech Decoders](https://mlsanity.com/paper/2609.31992/) (2026-09-25)