The recent Deepseek paper used LogitLens and CKA to analyze their new Engram architecture. This is the first time I’ve seen interpretability research be used in a capabilities paper, and I wonder if this trend will continue as the field of interpretability advances.
The recent Deepseek paper used LogitLens and CKA to analyze their new Engram architecture. This is the first time I’ve seen interpretability research be used in a capabilities paper, and I wonder if this trend will continue as the field of interpretability advances.