#

arbitrary-rank-ablation

Here is 1 public repository matching this topic...

Kasper-Bankler / llm-refusal-ablation-study

Studying how safety alignment is encoded in LLM weights, using Arbitrary-Rank Ablation to isolate and remove the refusal direction in Gemma 4 E2B.

ai-safety interpretability llm-safety gemma4 refusal-ablation arbitrary-rank-ablation

Updated Jul 23, 2026
Python

Improve this page

Add a description, image, and links to the arbitrary-rank-ablation topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the arbitrary-rank-ablation topic, visit your repo's landing page and select "manage topics."