arxiv:2310.08164
Abdullah
amirabdullah19852020
AI & ML interests
Mechanistic interpretability, high dimensional geometry, persona role playing.
Recent Activity
updated
a collection
about 13 hours ago
TinySQL
Organizations
Papers
1
models
17
amirabdullah19852020/base_llama_1b_sae
Updated
amirabdullah19852020/interpreting_reward_models
Updated
amirabdullah19852020/test
Text Generation
•
Updated
•
17
amirabdullah19852020/gpt-neo-125m_hh_reward
Text Generation
•
Updated
•
14
amirabdullah19852020/gpt-neo-125m_utility_reward
Reinforcement Learning
•
Updated
•
17
amirabdullah19852020/pythia-70m_sentiment_reward
Reinforcement Learning
•
Updated
•
6
amirabdullah19852020/pythia-160m_sentiment_reward
Reinforcement Learning
•
Updated
•
21
amirabdullah19852020/gpt-neo-125m_sentiment_reward
Reinforcement Learning
•
Updated
•
17
amirabdullah19852020/pythia-160m_utility_reward
Reinforcement Learning
•
Updated
•
20
amirabdullah19852020/pythia-70m_utility_reward
Reinforcement Learning
•
Updated
•
18