Parents :
Neural network interpretability
Amis :
 
ExpandDescendants
3 Documents (Liste longue) 
Sanjeev Arora sur Twitter : "new `skills' induced by LLM fine-tuning can be localized in tiny fraction of the model."
Tags:
2023-07-07 A propos
Designing and Interpreting Probes · John Hewitt
Tags:
2020-08-02 A propos
The Building Blocks of Interpretability
Tags:
2018-03-07 A propos
Propriétés