Reproduce “Sparse Autoencoders enable Robust and Interpretable Fine-tuning of CLIP models” 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
Fabian Morelli, Arnas Uselis, Ankit Sonthalia, Seong Joon Oh
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.