arxiv:2310.08164
Abdullah
amirabdullah19852020
AI & ML interests
Mechanistic interpretability, high dimensional geometry, persona role playing.
Recent Activity
updated
a collection
26 days ago
Transferring Activation Features for model interventions
published
a dataset
26 days ago
withmartian/binary_bbq
updated
a model
about 1 month ago
withmartian/trained_mediqa_model
Organizations
models
17
amirabdullah19852020/base_llama_1b_sae
Updated
amirabdullah19852020/interpreting_reward_models
Updated
amirabdullah19852020/test
Text Generation
•
0.1B
•
Updated
•
6
amirabdullah19852020/gpt-neo-125m_hh_reward
Text Generation
•
0.1B
•
Updated
•
11
amirabdullah19852020/gpt-neo-125m_utility_reward
Reinforcement Learning
•
Updated
•
7
amirabdullah19852020/pythia-70m_sentiment_reward
Reinforcement Learning
•
Updated
•
9
amirabdullah19852020/pythia-160m_sentiment_reward
Reinforcement Learning
•
Updated
•
8
amirabdullah19852020/gpt-neo-125m_sentiment_reward
Reinforcement Learning
•
Updated
•
9
amirabdullah19852020/pythia-160m_utility_reward
Reinforcement Learning
•
Updated
•
8
amirabdullah19852020/pythia-70m_utility_reward
Reinforcement Learning
•
0.1B
•
Updated
•
11