Pinned Loading
-
Refusal-Direction-A-Small-Scale-Replication
Refusal-Direction-A-Small-Scale-Replication PublicA small-scale replication of Arditi et al. (2024) "Refusal in Language Models Is Mediated by a Single Direction": extracting a refusal direction in Qwen2.5-1.5B-Instruct via difference-of-means, th…
Jupyter Notebook
-
SAiDL-Summer-Assignment-2026
SAiDL-Summer-Assignment-2026 PublicA repository documenting my attempt of the induction assignment. Secondary task chosen: Mechanistic Interpretability.
Jupyter Notebook
-
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.