amirali1985/high-temp-refusal-mech-interp download history

amirali1985/high-temp-refusal-mech-interp is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 208 times (27 in the last 7 days), and 208 times in total. It ranks #65,902 among datasets by monthly downloads.

High-Temperature Refusal Mechanistic Interpretability Artifacts This dataset repository contains the machine-readable artifacts for the gated Qwen2.5-7B-Instruct mechanistic-interpretability campaign documented in MECH_INTERP_RESULTS.md. The core artifacts include: all-layer greedy r

Open amirali1985/high-temp-refusal-mech-interp on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.