Search Results
Metalearning & Induction Heads [rough early thoughts]
Attention - General - Copying & Induction heads [rough early thoughts]
2L Attention - Results [rough early thoughts]
"Induction Bump" Phase Change [rough early thoughts]
A Walkthrough of In-Context Learning and Induction Heads Part 1 of 2 (w/ Charles Frye)
Attention - General - Indirect & n-gram Attention Heads [rough early thoughts]
Understanding ICL: Induction Heads (Natural Language Processing at UT Austin)
1L Attention - Results [rough early thoughts]
Stanford CS25: V1 I Transformer Circuits, Induction Heads, In-Context Learning
Catherine Olsson - Induction Heads
MLP Neurons - Privileged vs Non-Privileged Basis [rough early thoughts]
Sewoong Oh: Do Meta-learning and Federated Learning Find Good Representations?