Statements (25)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:person
|
| gptkbp:award |
gptkb:AI_Alignment_Prize
|
| gptkbp:education |
gptkb:University_of_Cambridge
|
| gptkbp:employer |
gptkb:DeepMind
|
| gptkbp:field |
gptkb:artificial_intelligence
gptkb:machine_learning interpretability |
| gptkbp:knownFor |
transformer models
circuit analysis in neural networks mechanistic interpretability |
| gptkbp:nationality |
British
|
| gptkbp:notableWork |
gptkb:A_Mathematical_Framework_for_Transformer_Circuits
gptkb:Toy_Models_of_Superposition gptkb:Transformer_Circuits Exploring Neuron Circuits in Language Models Progress Measures for Grokking via Mechanistic Interpretability |
| gptkbp:occupation |
gptkb:researchers
|
| gptkbp:publishedIn |
gptkb:Distill
gptkb:arXiv gptkb:LessWrong |
| gptkbp:twitter |
@NeelNanda5
|
| gptkbp:website |
https://www.neelnanda.io/
|
| gptkbp:bfsParent |
gptkb:Open_Philanthropy_Project
|
| gptkbp:bfsLayer |
6
|
| https://www.w3.org/2000/01/rdf-schema#label |
Neel Nanda
|