Statements (15)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
online discussion thread
|
| gptkbp:createdBy |
gptkb:Neel_Nanda
|
| gptkbp:dateCreated |
2021
|
| gptkbp:discusses |
circuit analysis
mechanistic interpretability ML research attention heads |
| https://www.w3.org/2000/01/rdf-schema#label |
Transformer Circuits Thread
|
| gptkbp:platform |
gptkb:LessWrong
|
| gptkbp:relatedTo |
transformer circuits
|
| gptkbp:topic |
interpretability
transformer neural networks |
| gptkbp:url |
https://www.lesswrong.com/posts/5g5TkQ6L5r5Qm9KzF/transformer-circuits-thread
|
| gptkbp:bfsParent |
gptkb:Transformer_Circuits
|
| gptkbp:bfsLayer |
8
|