Haotian Ma PRO
Hunter26666666
·
AI & ML interests
I develop methods to understand how learned representations shape model behavior across interventions, combinations, and changing contexts.
Recent Activity
updated a collection 6 days ago
Interpretable AI for Scientific Discovery upvoted a paper 6 days ago
AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse
Autoencoders upvoted a collection 6 days ago
Interpretable AI for Scientific DiscoveryOrganizations