2 3 1

Abdullah

amirabdullah19852020

amirabdullah19852020

AI & ML interests

Mechanistic interpretability, high dimensional geometry, persona role playing.

Recent Activity

published a model 1 day ago

withmartian/sql_interp_saes

updated a dataset 11 days ago

withmartian/binary_toxic

published a dataset 11 days ago

withmartian/binary_toxic

View all activity

Organizations

models 17

amirabdullah19852020/base_llama_1b_sae

Updated Dec 26, 2024

amirabdullah19852020/interpreting_reward_models

Updated Aug 7, 2024

amirabdullah19852020/test

Text Generation • Updated May 8, 2024 • 3

amirabdullah19852020/gpt-neo-125m_hh_reward

Text Generation • Updated Apr 27, 2024

amirabdullah19852020/gpt-neo-125m_utility_reward

Reinforcement Learning • Updated Feb 10, 2024 • 3

amirabdullah19852020/pythia-70m_sentiment_reward

Reinforcement Learning • Updated Feb 10, 2024 • 7

amirabdullah19852020/pythia-160m_sentiment_reward

Reinforcement Learning • Updated Feb 10, 2024 • 7

amirabdullah19852020/gpt-neo-125m_sentiment_reward

Reinforcement Learning • Updated Feb 10, 2024 • 3

amirabdullah19852020/pythia-160m_utility_reward

Reinforcement Learning • Updated Feb 10, 2024 • 3

amirabdullah19852020/pythia-70m_utility_reward

Reinforcement Learning • Updated Feb 10, 2024 • 6

datasets 2

amirabdullah19852020/rebuttal_med_qa

Viewer • Updated Mar 27 • 257k • 73

amirabdullah19852020/interpreting_reward_models

Updated May 4, 2024 • 3

Abdullah

AI & ML interests

Recent Activity

Organizations

Papers 1

spaces 1

Interpreting Reward Models

models 17 Sort: Recently updated

datasets 2 Sort: Recently updated

models 17

datasets 2