Ben Hoover
bhoov
AI & ML interests
Interpretability, NLP, Hopfield Nets
Recent Activity
upvoted
a
paper
19 days ago
Effective Red-Teaming of Policy-Adherent Agents
upvoted
a
paper
5 months ago
ConceptAttention: Diffusion Transformers Learn Highly Interpretable
Features
authored
a paper
11 months ago
DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image
Generative Models