Reproduce “Faithful and Stable Neuron Explanations for Trustworthy Mechanistic Interpretability” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Ge Yan, Tuomas Oikarinen, Tsui-Wei, Weng

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.