amirabdullah19852020/base_llama_1b_sae
Updated
Abdullah
amirabdullah19852020
AI & ML interests
Mechanistic interpretability, high dimensional geometry, persona role playing.
Recent Activity
updated
a collection
15 days ago
Transferring Activation Features for model interventions
published
a dataset
15 days ago
withmartian/binary_bbq
updated
a model
25 days ago
withmartian/trained_mediqa_model
Organizations
amirabdullah19852020/interpreting_reward_models
Updated
amirabdullah19852020/test
Text Generation
•
0.1B
•
Updated
•
43
amirabdullah19852020/gpt-neo-125m_hh_reward
Text Generation
•
0.1B
•
Updated
•
15
amirabdullah19852020/gpt-neo-125m_utility_reward
Reinforcement Learning
•
Updated
•
78
amirabdullah19852020/pythia-70m_sentiment_reward
Reinforcement Learning
•
Updated
•
20
amirabdullah19852020/pythia-160m_sentiment_reward
Reinforcement Learning
•
Updated
•
26
amirabdullah19852020/gpt-neo-125m_sentiment_reward
Reinforcement Learning
•
Updated
•
55
amirabdullah19852020/pythia-160m_utility_reward
Reinforcement Learning
•
Updated
•
18
amirabdullah19852020/pythia-70m_utility_reward
Reinforcement Learning
•
0.1B
•
Updated
•
21
amirabdullah19852020/gpt-j-6b-sharded-bf16_sentiment_reward
Reinforcement Learning
•
Updated
amirabdullah19852020/pythia-410m_utility_reward
Reinforcement Learning
•
Updated
•
23
amirabdullah19852020/pythia-410m_sentiment_reward
Reinforcement Learning
•
Updated
•
15
amirabdullah19852020/pythia_70m_ppo_imdb_sentiment_with_checkpoints
Reinforcement Learning
•
Updated
•
12
amirabdullah19852020/pythia_70m_ppo_imdb_sentiment_v3
Reinforcement Learning
•
Updated
•
71
amirabdullah19852020/pythia_70m_ppo_imdb_sentiment_v2
Reinforcement Learning
•
Updated
•
20
amirabdullah19852020/pythia_70m_ppo_imdb_sentiment
Reinforcement Learning
•
Updated
•
18