Successor Heads: Recurring, Interpretable Attention Heads In The Wild
Paper
•
2312.09230
•
Published
Euan Ong
euanong
AI & ML interests
None yet
Recent Activity
authored
a paper
7 days ago
Successor Heads: Recurring, Interpretable Attention Heads In The Wild
authored
a paper
7 days ago
Learnable Commutative Monoids for Graph Neural Networks
authored
a paper
7 days ago
Constitutional Classifiers: Defending against Universal Jailbreaks
across Thousands of Hours of Red Teaming
Organizations
None yet