Circuit-Tracer: A New Library for Finding Feature Circuits

Michael Hanna, Mateusz Piotrowski, Jack Lindsey, Emmanuel Ameisen

Keywords: Interpretability tooling and software, Sparse Autoencoders, Circuit analysis

Other Keywords: transcoders

TL;DR: We introduce circuit-tracer, a library for finding, visualizing, and working with feature circuits.

Abstract: Feature circuits aim to shed light on LLM behavior by identifying the features that are causally responsible for a given LLM output, and connecting them into a directed graph, or *circuit*, that explains how both each feature and each output arose. However, performing circuit analysis is challenging: the tools for finding, visualizing, and verifying feature circuits are complex and spread across libraries. To facilitate feature-circuit finding, we introduce `circuit-tracer`, an open-source library for efficient identification of feature circuits. `circuit-tracer` provides an integrated pipeline for finding, visualizing, annotating, and performing interventions on such circuits, tested with various model sizes, up to 14B parameters. We make `circuit-tracer` available to both developers and end users, via integration with tools such as Neuronpedia, which provides a user-friendly interface.

Submission Number: 50