ML Wiki
Search
Search
Explorer
Tag: mechanistic-interpretability
2 items with this tag.
May 03, 2026
Probing (Neural Network Interpretability)
concept
interpretability
mechanistic-interpretability
May 03, 2026
Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task (Othello-GPT)
source
mechanistic-interpretability
probing
emergent-behavior
transformer
in-context-learning