2026-03-08 | IOI Transformer
Goal: Implement Transformer from Scratch | Train on IOI Task
Summary: Battle Einsum Notation for the QK Attention Pattern
Work sessions
| In | Out |
|---|---|
| 08:30 | 09:30 |
Use the same dataset strategy as Emergence of Minimal Circuits for Indirect Object Identification in Attention-Only Transformers