Statements (19)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:academic_journal
|
| gptkbp:arXivID |
2301.09721
|
| gptkbp:author |
gptkb:Neel_Nanda
|
| gptkbp:citation |
100+
|
| gptkbp:codename |
https://github.com/neelnanda-io/toy-models-of-superposition
|
| gptkbp:explores |
how neural networks represent more features than they have dimensions
|
| gptkbp:field |
gptkb:artificial_intelligence
gptkb:machine_learning interpretability |
| gptkbp:focusesOn |
mechanistic interpretability
superposition in neural networks |
| https://www.w3.org/2000/01/rdf-schema#label |
Toy Models of Superposition
|
| gptkbp:influencedBy |
mechanistic interpretability research
|
| gptkbp:proposedBy |
toy models to study superposition
|
| gptkbp:publicationYear |
2023
|
| gptkbp:publishedIn |
gptkb:arXiv
|
| gptkbp:url |
https://arxiv.org/abs/2301.09721
|
| gptkbp:bfsParent |
gptkb:Neel_Nanda
|
| gptkbp:bfsLayer |
7
|