Search Results for author:
Found 2 papers, 2 papers with code
Explorations of Self-Repair in Language Models
Prior interpretability research studying narrow distributions has preliminarily identified self-repair, a phenomena where if components in large language models are ablated, later components will change their behavior to compensate.
Copy Suppression: Comprehensively Understanding an Attention Head
We show that self-repair is implemented by several mechanisms, one of which is copy suppression, which explains 39% of the behavior in a narrow task.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
