A Mathematical Framework for Transformer Circuits
GPTKB entity
Statements (21)
Predicate | Object |
---|---|
gptkbp:instanceOf |
gptkb:academic_journal
|
gptkbp:arXivID |
2309.00906
|
gptkbp:author |
gptkb:Nick_Cammarata
gptkb:Tom_Lieberum gptkb:Shan_Carter gptkb:Catherine_Olsson gptkb:Chris_Olah gptkb:Nelson_Elhage gptkb:Neel_Nanda |
gptkbp:field |
gptkb:machine_learning
transformer models mechanistic interpretability |
gptkbp:focusesOn |
decomposition of transformer computations
interpretability of neural networks mathematical analysis of transformer circuits |
https://www.w3.org/2000/01/rdf-schema#label |
A Mathematical Framework for Transformer Circuits
|
gptkbp:publicationYear |
2023
|
gptkbp:publishedIn |
gptkb:arXiv
|
gptkbp:url |
https://arxiv.org/abs/2309.00906
|
gptkbp:bfsParent |
gptkb:Neel_Nanda
|
gptkbp:bfsLayer |
7
|