Abdullah PRO

amirali1985

·

amirabdullah19852020

AI & ML interests

Mechanistic interpretability, high dimensional geometry, persona role playing.

Recent Activity

updated a dataset 11 minutes ago

curveball-steering/eval_results

updated a dataset about 3 hours ago

curveball-steering/conversations_corrigible_more_qwen2.5-1.5B-it_large

published a dataset about 3 hours ago

curveball-steering/conversations_corrigible_more_qwen2.5-1.5B-it_large

View all activity

Organizations

New activity in stride-influence/attribution-comparison 4 months ago

AirRep vs STRIDE vs LoGRA — preliminary comparison results

#1 opened 4 months ago by

New activity in thoughtworks/gemma_psychometrics_personas_responses 4 months ago

can y you put a license on this please?

#2 opened 4 months ago by

New activity in amirali1985/pythia-70m_utility_reward almost 3 years ago

Adding `safetensors` variant of this model

#1 opened almost 3 years ago by