Cached layer activations for steering vector experiments
Abdullah
amirali1985
AI & ML interests
Mechanistic interpretability, high dimensional geometry, persona role playing.
Recent Activity
updated a model about 22 hours ago
thoughtworks/cbd-gemma2-100pair-robust-wip updated a dataset 4 days ago
amirali1985/high-temp-refusal-probe-artifacts published a dataset 5 days ago
amirali1985/high-temp-refusal-probe-artifactsOrganizations
-
amirali1985/convsersations_corrigible_more_llama3.2-1B-it_large_with_curvature
Viewer • Updated • 8.27k • 7 -
amirali1985/convsersations_power_seeking_llama3.2-1B-it_large_with_curvature
Viewer • Updated • 8.27k • 8 -
amirali1985/convsersations_self_awareness_general_llama3.2-1B-it_large_with_curvature
Viewer • Updated • 10k • 15 -
amirali1985/convsersations_sadness_llama3.2-1B-it_large_with_curvature
Viewer • Updated • 9.78k • 11
Cached layer activations for steering vector experiments
-
amirali1985/convsersations_corrigible_more_llama3.2-1B-it_large_with_curvature
Viewer • Updated • 8.27k • 7 -
amirali1985/convsersations_power_seeking_llama3.2-1B-it_large_with_curvature
Viewer • Updated • 8.27k • 8 -
amirali1985/convsersations_self_awareness_general_llama3.2-1B-it_large_with_curvature
Viewer • Updated • 10k • 15 -
amirali1985/convsersations_sadness_llama3.2-1B-it_large_with_curvature
Viewer • Updated • 9.78k • 11
models 15
amirali1985/interpreting_reward_models
Updated
amirali1985/gpt-neo-125m_hh_reward
Text Generation • 0.1B • Updated • 4
amirali1985/gpt-neo-125m_utility_reward
Reinforcement Learning • Updated • 2
amirali1985/pythia-70m_sentiment_reward
Reinforcement Learning • Updated • 2
amirali1985/pythia-160m_sentiment_reward
Reinforcement Learning • Updated • 4
amirali1985/gpt-neo-125m_sentiment_reward
Reinforcement Learning • Updated • 3
amirali1985/pythia-160m_utility_reward
Reinforcement Learning • Updated • 1
amirali1985/pythia-70m_utility_reward
Reinforcement Learning • 70.4M • Updated • 3
amirali1985/gpt-j-6b-sharded-bf16_sentiment_reward
Reinforcement Learning • Updated
amirali1985/pythia-410m_utility_reward
Reinforcement Learning • Updated • 1
datasets 26
amirali1985/high-temp-refusal-probe-artifacts
Viewer • Updated • 1 • 126
amirali1985/convsersations_sadness_llama3.1-8B-it_large
Viewer • Updated • 9.78k • 52
amirali1985/convsersations_excitement_llama3.1-8B-it_large
Viewer • Updated • 8k • 10
amirali1985/convsersations_rude_llama3.1-8B-it_large
Viewer • Updated • 15.9k • 9
amirali1985/convsersations_humor_llama3.1-8B-it_large
Viewer • Updated • 9.63k • 7
amirali1985/convsersations_corrigible_more_llama3.1-8B-it_large
Viewer • Updated • 8.27k • 9
amirali1985/convsersations_power_seeking_llama3.1-8B-it_large
Viewer • Updated • 8.27k • 10
amirali1985/convsersations_wealth_seeking_llama3.1-8B-it_large
Viewer • Updated • 11.4k • 3
amirali1985/convsersations_self_awareness_general_llama3.1-8B-it_large
Viewer • Updated • 13.4k • 3
amirali1985/llama3.2-1B-it_power_seeking_layer10
Viewer • Updated • 8.27k • 5