Mechanistic Interpretability skills

13 tagged Mechanistic Interpretability, measured the same way as everything else here.

Browse within: ai-scientist 88 agents 85 ai-systems 85 artificial-intelligence 85 large-language-models 85 Feature Discovery 7 SAE 7 Sparse Autoencoders 7 Superposition 7 Activation Patching 6 Circuit Analysis 6 Model Internals 6 NDIF 6 Remote Execution 6

Sort Relevance Recently updated Fewest tokens Security grade Repo stars Stars this week Top rated 13 mods

Nothing here yet

This corner of the catalogue is empty. The crawl runs nightly, so it may not be for long.