Vector Label
refusal (Arditi et al. 2024)Model
gemma-2-2b-it
Layer #
15
Steering Hook
blocks.15.hook_resid_pre
Steering Strength
0.25
Uploader
bot-neuronpedia
Created At
11/20/2024 9:49:19 AM
Raw Vector
Actions
Explanations
No Explanations Found
New Auto-Interp