Reproduce “What Does Activation Steering Control? Attribution Across Answer Encodings and Output-Sensitive Subspaces” 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
Zhiwei Gao, Shaowen Peng, Shoko Wakamiya, Eiji Aramaki
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.