Emmanuel Watila's picture

Emmanuel Watila

devsgnr
1
·

AI & ML interests

AI Safety & Alignment, Interpretability (Feature Attribution & Mechanistic Interpretability), Supervised Fine-Tuning

Recent Activity

upvoted an article about 10 hours ago
J-Space: Yet Another LLM Mind Reader?
updated a dataset 4 days ago
devsgnr/bio-safety-peft-lora
published a dataset 4 days ago
devsgnr/bio-safety-peft-lora
View all activity

Organizations

None yet