Aruna S

arunasank
·

AI & ML interests

Interpretability, AI & Society, models vs the brain

Recent Activity

updated a model 1 day ago
arunasank/sae-scoping-recover
published a model 1 day ago
arunasank/sae-scoping-recover
updated a model 26 days ago
arunasank/sae-filters
View all activity

Organizations

Massachusetts Institute of Technology's profile picture Mechanistic Interpretability Benchmark's profile picture