Attribution Patching Outperforms Automated Circuit Discovery (2023 · 81 citations)
Mechanistic interpretability tries to find circuits, which are small subgraphs of a network that account for a specific behavior. Automated tools such as ACDC rely on activation patching. That method needs an extra forward pass for each edge it tests, so it scales poorly to large models.
The Quest for the Right Mediator: Surveying Mechanistic Interpretability for NLP Through the Lens of Causal Mediation Analysis (2026 · 7 citations)
Research on mechanistic interpretability (MI) of language models is fragmented. Studies use bespoke evaluations, lack a shared theoretical basis, and rarely define the elementary causal units that make up a "mechanism." This survey, published in Computational Linguistics, treats MI as recovering causal graphs that…

Co-authors here

10 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 74 times (of the 149,439 papers whose bibliographies we read); 13 citing papers with a page here →.

Updated 2 November 2026