psidharth567/mech_interp_experiments download history

psidharth567/mech_interp_experiments is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 100 times (25 in the last 7 days), and 1,453 times in total. It ranks #114,791 among datasets by monthly downloads.

Attack / critic / defender template experiments Python tooling for prompt-injection template search, evaluation against a target model, and optional defender stress tests. Start here for humans: skim AGENTS.md (written for AI agents and contributors). Quick start Environment:

Open psidharth567/mech_interp_experiments on Hugging Face

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