Entities · Models
GPT-2 small
8 articles tagged with this entity.
-
Rift: A Conflict Signature for Deception in Language Models
-
LiFT: Local Search via Linear Programming for Overfitting-Controlled Transformers
-
Pre-Intervention Prediction of Sparse Autoencoder Steering Side Effects
-
Trajectory Dynamics in Language Model Hidden States Predict Human Processing Costs Beyond Surprisal
-
How Much Orthogonalization Does Muon Need?
-
MechRL: Reinforcement Learning Agents Perform Circuit Discovery for Mechanistic Interpretability
-
Every Component is a Lookup: Token Attribution and Composition from a Single Decomposition
-
When and Why Grouping Attention Heads Accelerates Muon Optimization