aq1048576/red_team_agent_analysis_rl_csvs_diverse1_correlation_summary
Viewer
• Updated
• 5 • 7
A Q
aq1048576
AI & ML interests
None yet
Organizations
None yet
aq1048576/red_team_agent_analysis_rl_csvs_bob
Viewer
• Updated
• 5 • 12
aq1048576/red_team_agent_analysis_rl_attributions1
Viewer
• Updated
• 64 • 10
aq1048576/red_team_agent_analysis_rl_attributions
Viewer
• Updated
• 64 • 25
aq1048576/red_team_agent_analysis_zexample7
Viewer
• Updated
• 256 • 9
aq1048576/red_team_agent_analysis_zexample6
Viewer
• Updated
• 100 • 26
aq1048576/red_team_agent_analysis_queries
Viewer
• Updated
• 5k • 31
aq1048576/red_team_agent_analysis_multilingual_story_analysis_detailed
Viewer
• Updated
• 1k • 9
aq1048576/red_team_agent_analysis_claude_reconstruction_test_results
Viewer
• Updated
• 100 • 10
aq1048576/bob2
Viewer
• Updated
• 6 • 36
aq1048576/bob
Viewer
• Updated
• 10 • 7
aq1048576/sample-a-lot-scored
Viewer
• Updated
• 319k • 6
aq1048576/sample-a-lot-no-scoring
Viewer
• Updated
• 2.05M • 6
aq1048576/0901-no_sexism_rl_prompts
Viewer
• Updated
• 240k • 4
aq1048576/wildchat-category-generation-distinct-combined
Viewer
• Updated
• 11.2M • 6
aq1048576/0831-no_sexism_rl_prompts
Viewer
• Updated
• 240k • 4
aq1048576/0830-no_sexism_rl_prompts
Viewer
• Updated
• 240k • 4
aq1048576/consistent_sexism_filter_c4_250000_queries_500000_pairs_train_pairs-batch
Viewer
• Updated
• 500k • 6
aq1048576/consistent_sexism_filter_c4_250000_queries_500000_pairs_train_pairs
Viewer
• Updated
• 500k • 4
aq1048576/0829-no_sexism_rl_prompts
Viewer
• Updated
• 240k • 4
aq1048576/consistent_sexism_filter_c4_71410_queries_100000_pairs_test_pairs-batch
Viewer
• Updated
• 100k • 4
aq1048576/consistent_sexism_filter_c4_71410_queries_100000_pairs_test_pairs
Viewer
• Updated
• 100k • 4
aq1048576/consistent_sexism_filter_c4_500000_queries_500000_pairs_train_pairs-batch
Viewer
• Updated
• 500k • 4
aq1048576/consistent_sexism_filter_c4_500000_queries_500000_pairs_train_pairs
Viewer
• Updated
• 500k • 6
aq1048576/0827-no_sexism_rl_prompts
Viewer
• Updated
• 240k • 4
aq1048576/consistent_sexism_filter_c4_250000_queries_500000_pairs_train_queries
Viewer
• Updated
• 250k • 4
aq1048576/consistent_sexism_filter_c4_71410_queries_100000_pairs_test_queries
Viewer
• Updated
• 71.4k • 4
aq1048576/consistent_sexism_filter_c4_500000_queries_500000_pairs_train_queries
Viewer
• Updated
• 499k • 4
aq1048576/c1sexism_filter_c4_500000_queries_500000_pairs_train_pairs-batch
Viewer
• Updated
• 500k • 6
aq1048576/c1sexism_filter_c4_500000_queries_500000_pairs_train_pairs
Viewer
• Updated
• 500k • 4