2 6 2

Abdullah

amirali1985

amirabdullah19852020

AI & ML interests

Mechanistic interpretability, high dimensional geometry, persona role playing.

Recent Activity

updated a model 5 days ago

apart/saes-llama3.2-1b-base-smollm-1m

published a model 5 days ago

apart/saes-llama3.2-1b-base-smollm-1m

updated a model 6 days ago

apart/llama3.2_1b_instruct_saes_vader

View all activity

Organizations

Generate inferred truth values from PSL rules and hypotheses

No application file

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 • 14

amirali1985/gpt-neo-125m_utility_reward

Reinforcement Learning • Updated Feb 10, 2024 • 22

amirali1985/pythia-70m_sentiment_reward

Reinforcement Learning • Updated Feb 10, 2024 • 21

amirali1985/pythia-160m_sentiment_reward

Reinforcement Learning • Updated Feb 10, 2024 • 14

amirali1985/gpt-neo-125m_sentiment_reward

Reinforcement Learning • Updated Feb 10, 2024 • 22

amirali1985/pythia-160m_utility_reward

Reinforcement Learning • Updated Feb 10, 2024 • 22

amirali1985/pythia-70m_utility_reward

Reinforcement Learning • 70.4M • Updated Feb 10, 2024 • 16

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 • 21

View 15 models

datasets 2

amirali1985/rebuttal_med_qa

Viewer • Updated Mar 27 • 257k • 7

amirali1985/interpreting_reward_models

Updated May 4, 2024 • 1

Abdullah

AI & ML interests

Recent Activity

Organizations

Papers 1

spaces 2 Sort: Recently updated

PSL Demo Minimality Circuit

Interpreting Reward Models

models 15 Sort: Recently updated

datasets 2 Sort: Recently updated

spaces 2

models 15

datasets 2