arxiv:2310.08164
Abdullah
amirali1985
AI & ML interests
Mechanistic interpretability, high dimensional geometry, persona role playing.
Recent Activity
updated
a dataset
3 minutes ago
amirali1985/convsersations_corrigible_more_llama3.2-1B-it_large_with_curvature
published
a dataset
about 7 hours ago
amirali1985/convsersations_corrigible_more_llama3.2-1B-it_large_with_curvature
updated
a dataset
about 7 hours ago
amirali1985/convsersations_corrigible_more_llama3.2-1B-it_large
Organizations
models
15
amirali1985/interpreting_reward_models
Updated
amirali1985/gpt-neo-125m_hh_reward
Text Generation
•
0.1B
•
Updated
•
2
amirali1985/gpt-neo-125m_utility_reward
Reinforcement Learning
•
Updated
•
5
amirali1985/pythia-70m_sentiment_reward
Reinforcement Learning
•
Updated
•
6
amirali1985/pythia-160m_sentiment_reward
Reinforcement Learning
•
Updated
•
5
amirali1985/gpt-neo-125m_sentiment_reward
Reinforcement Learning
•
Updated
•
5
amirali1985/pythia-160m_utility_reward
Reinforcement Learning
•
Updated
•
5
amirali1985/pythia-70m_utility_reward
Reinforcement Learning
•
70.4M
•
Updated
•
2
amirali1985/gpt-j-6b-sharded-bf16_sentiment_reward
Reinforcement Learning
•
Updated
amirali1985/pythia-410m_utility_reward
Reinforcement Learning
•
Updated
•
4
datasets
6
amirali1985/convsersations_corrigible_more_llama3.2-1B-it_large_with_curvature
Viewer
•
Updated
•
8.27k
•
3
amirali1985/convsersations_corrigible_more_llama3.2-1B-it_large
Viewer
•
Updated
•
8.27k
•
2
amirali1985/debate_style_agnostic_questions
Viewer
•
Updated
•
800
amirali1985/tone_agnostic_questions
Viewer
•
Updated
•
800
•
1
amirali1985/rebuttal_med_qa
Viewer
•
Updated
•
257k
•
1
amirali1985/interpreting_reward_models
Updated
•
1