circuit-tracer

circuit-tracer is a collaborative mechanistic interpretability project that implements tools for discovering and analyzing feature circuits in large language models. Building on sparse autoencoders and transcoders, it identifies features that are causally responsible for particular outputs, assembles them into directed attribution graphs, and exposes APIs for visualizing and editing these circuits. The library was initially developed by Anthropic fellows and released as open source; it is maintained in close collaboration with Decode Research, which hosts the decoderesearch/circuit-tracer repository and provides a Neuronpedia integration so that researchers can run circuit tracing through an interactive web interface without needing local setup. circuit-tracer has been used in downstream work on circuit tracing in both language and vision-language models and is part of a broader ecosystem of interpretability tools around Neuronpedia and SAELens.

Endorsements support Decode Research.

No endorsements yet.

Discussion

Start Date

-

End Date

-

Expected Duration

-

Funding Raised to Date

-