🤝 Open to Collab

Matteo He

hematteo

·

https://matteohe.com

AI & ML interests

Generative AI, Mechanistic Interpretability, AI Safety, Post-Training, Reinforcement Learning

Recent Activity

updated a Space 5 days ago

hematteo/readout-feature-atlas

upvoted a paper 5 days ago

Self-Evolving Agent Harness

liked a model 5 days ago

meta-models/Muse-Spark-Open-816B-A42B

View all activity

Organizations

upvoted a paper 5 days ago

Self-Evolving Agent Harness

Paper • 2610.18813 • Published 9 days ago • 220

upvoted a paper 6 days ago

Learning to Read Out: Unembedding Dynamics in Language Model Pretraining

Paper • 2610.21025 • Published 8 days ago • 10

upvoted a paper about 2 months ago

Sparse Readout Prism: Explaining Logit-Lens Scores in Features Instead of Tokens

Paper • 2609.01936 • Published Sep 1 • 3