abotresol/gemma3-refusal-axis-data download history

abotresol/gemma3-refusal-axis-data is a feature extraction dataset on the Hugging Face Hub. In the last 30 days it was downloaded 44 times (11 in the last 7 days), and 8,578 times in total. It ranks #203,866 among datasets by monthly downloads.

Gemma 3 12B Refusal Axis: Activations and SAE Encodings Mechanistic interpretability data for studying the refusal axis in Gemma 3 12B-IT. This dataset contains the layer-41 residual-stream activations and Gemma Scope 2 SAE encodings produced by running 280 contrastive prompt pairs throug

Open abotresol/gemma3-refusal-axis-data on Hugging Face

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