No application file
Interpreting Reward Models
🦀
Abdullah
amirabdullah19852020
AI & ML interests
Mechanistic interpretability, high dimensional geometry, persona role playing.
Recent Activity
upvoted
a
paper
6 days ago
Activation Space Interventions Can Be Transferred Between Large Language
Models
updated
a collection
6 days ago
Transferring Activation Features for model interventions
updated
a collection
about 2 months ago
Transferring Activation Features for model interventions
Organizations
