Mechanistic Interpretability Community
GPTKB entity
Statements (15)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:community
|
| gptkbp:aimsTo |
advance understanding of neural networks
improve transparency of AI systems |
| gptkbp:focusesOn |
mechanistic interpretability
|
| https://www.w3.org/2000/01/rdf-schema#label |
Mechanistic Interpretability Community
|
| gptkbp:organizes |
workshops
reading groups |
| gptkbp:relatedTo |
AI safety
alignment research machine learning interpretability |
| gptkbp:socialMedia |
gptkb:Discord
gptkb:LessWrong gptkb:Alignment_Forum |
| gptkbp:bfsParent |
gptkb:Transformer_Circuits
|
| gptkbp:bfsLayer |
8
|