Mechanistic interpretability — citation graph of key research
Explore the most influential research on mechanistic interpretability as an interactive citation graph on Constellation. The papers below are connected by direct citations and shared references — open any one to center the graph on it and discover related work.
Top papers on mechanistic interpretability
- Mechanistic Interpretability for AI Safety -- A Review
Leonard F. Bereska, Efstratios Gavves — 2024 · arXiv (Cornell University) · 31 citations - Explaining AI through mechanistic interpretability
Lena Kästner, Barnaby Crook — 2024 · European Journal for Philosophy of Science · 42 citations - Open Problems in Mechanistic Interpretability
Lee Sharkey, Bilal I. Chughtai, Joshua Batson et al. — 2025 · arXiv (Cornell University) · 11 citations - MIB: A Mechanistic Interpretability Benchmark
Aaron Mueller, Atticus Geiger, Sarah Wiegreffe et al. — 2025 · UvA-DARE (University of Amsterdam) · 1 citations - Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability
Atticus Geiger, Duligur Ibeling, Zur, Amir et al. — 2023 · arXiv (Cornell University) · 11 citations - Mechanistic Interpretability for Transformers in Financial Engineering
Edward Sharkey, Philip Colin Treleaven — 2025 · 1 citations - Survey on the Role of Mechanistic Interpretability in Generative AI
Leonardo Ranaldi — 2025 · Big Data and Cognitive Computing · 20 citations - The Misery of Mechanistic Interpretability: A Formal Perspective
Tobias Ladner, Matthias Althoff — 2026 · arXiv (Cornell University) - Mechanistic Interpretability: A New Trend in Interpretability Research
Koshiro Aoki, Ryota Takatsuki, Gouki Minegishi et al. — 2026 · Transactions of the Japanese Society for Artificial Intelligence - Mechanistic Interpretability of Large Language Models
Zen Revista — 2026 · Zenodo (CERN European Organization for Nuclear Research) - Mechanistic Interpretability of Reinforcement Learning Agents
Tristan Trim, Triston Grayston — 2024 · arXiv (Cornell University) - Mechanistic Interpretability of Binary and Ternary Transformers
Jason Li — 2024 · arXiv (Cornell University)