Abdullah's picture

2 2 1

Abdullah

amirabdullah19852020

·

amirabdullah19852020

AI & ML interests

Mechanistic interpretability, high dimensional geometry, persona role playing.

Organizations

Papers 1

arxiv:2310.08164

spaces 1

No application file

Interpreting Reward Models

models 17

amirabdullah19852020/base_llama_1b_sae

Updated about 21 hours ago

amirabdullah19852020/interpreting_reward_models

amirabdullah19852020/test

Text Generation • Updated May 8 • 19

amirabdullah19852020/gpt-neo-125m_hh_reward

Text Generation • Updated Apr 27 • 30

amirabdullah19852020/gpt-neo-125m_utility_reward

Reinforcement Learning • Updated Feb 10 • 9

amirabdullah19852020/pythia-70m_sentiment_reward

Reinforcement Learning • Updated Feb 10 • 12

amirabdullah19852020/pythia-160m_sentiment_reward

Reinforcement Learning • Updated Feb 10 • 13

amirabdullah19852020/gpt-neo-125m_sentiment_reward

Reinforcement Learning • Updated Feb 10 • 14

amirabdullah19852020/pythia-160m_utility_reward

Reinforcement Learning • Updated Feb 10 • 13

amirabdullah19852020/pythia-70m_utility_reward

Reinforcement Learning • Updated Feb 10 • 19

datasets 1

amirabdullah19852020/interpreting_reward_models

Updated May 4 • 4