Reproduce “PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits” 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
Maximilian Dreyer, Erblina Purelku, Johanna Vielhaben, Wojciech Samek, Sebastian Lapuschkin
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.