Abdullah's picture

2 8 5

Abdullah

amirali1985

·

amirabdullah19852020

AI & ML interests

Mechanistic interpretability, high dimensional geometry, persona role playing.

Recent Activity

updated a dataset about 1 hour ago

thoughtworks/psychometric_sjts_analysis_temp

published a dataset about 1 hour ago

thoughtworks/psychometric_sjts_analysis_temp

liked a dataset about 2 hours ago

thoughtworks/parliamentary_personas

View all activity

Organizations

Papers 1

arxiv:2310.08164

spaces 2

PSL for minimal circuits.

Visualize and analyze circuit minimality rules

Interpreting Reward Models

models 15

amirali1985/interpreting_reward_models

Updated Aug 7, 2024

amirali1985/gpt-neo-125m_hh_reward

Text Generation • 0.1B • Updated Apr 27, 2024 • 8

amirali1985/gpt-neo-125m_utility_reward

Reinforcement Learning • Updated Feb 10, 2024 • 12

amirali1985/pythia-70m_sentiment_reward

Reinforcement Learning • Updated Feb 10, 2024 • 13

amirali1985/pythia-160m_sentiment_reward

Reinforcement Learning • Updated Feb 10, 2024 • 17

amirali1985/gpt-neo-125m_sentiment_reward

Reinforcement Learning • Updated Feb 10, 2024 • 12

amirali1985/pythia-160m_utility_reward

Reinforcement Learning • Updated Feb 10, 2024 • 13

amirali1985/pythia-70m_utility_reward

Reinforcement Learning • 70.4M • Updated Feb 10, 2024 • 13

amirali1985/gpt-j-6b-sharded-bf16_sentiment_reward

Reinforcement Learning • Updated Sep 23, 2023

amirali1985/pythia-410m_utility_reward

Reinforcement Learning • Updated Sep 21, 2023 • 13

datasets 4

amirali1985/debate_style_agnostic_questions

Viewer • Updated Nov 16, 2025 • 800 • 1

amirali1985/tone_agnostic_questions

Viewer • Updated Nov 16, 2025 • 800 • 2

amirali1985/rebuttal_med_qa

Viewer • Updated Mar 27, 2025 • 257k • 9

amirali1985/interpreting_reward_models

Updated May 4, 2024 • 1