pinned
Running
Readout Feature Atlas
📖
Browse readout features across Pythia pretraining
🤝 Open to Collab
Matteo He
hematteo
AI & ML interests
Generative AI, Mechanistic Interpretability, AI Safety, Post-Training, Reinforcement Learning
Recent Activity
liked a dataset 1 day ago
msakarvadia/handwritten_multihop_reasoning_data liked a dataset 1 day ago
rmovva/HypotheSAEs liked a model 1 day ago
RobinHaselhorst/AMF-harrypotter-7bOrganizations
