DarianNLP/sae_feature_labels_REVISED
Viewer • Updated • 75 • 27
Darian Lee
DarianNLP
AI & ML interests
None yet
Recent Activity
updated a dataset 8 days ago
DarianNLP/sae_feature_labels_REVISED published a dataset 8 days ago
DarianNLP/sae_feature_labels_REVISED updated a dataset 14 days ago
DarianNLP/mda_sft_eval_topic_influencesOrganizations
None yet
DarianNLP/mda_sft_eval_topic_influences
Viewer • Updated • 240 • 54
DarianNLP/mda_influence_scores_NEW_lr1e4_cat_coded
Viewer • Updated • 220 • 97
DarianNLP/mda_step0_cache_NEW_with_labels_better
Viewer • Updated • 1 • 130
DarianNLP/mda_step0_cache_NEW_with_labels
Viewer • Updated • 1 • 138
DarianNLP/mda_influence_scores_NEW_lr1e4_v3
Viewer • Updated • 220 • 734
DarianNLP/mda_influence_scores_NEW_lr1e4_v2
Viewer • Updated • 220 • 499
DarianNLP/mda_influence_scores_NEW_lr1e4
Viewer • Updated • 216 • 307
DarianNLP/refusal_multimodel_dataset
Viewer • Updated • 10.8k • 542
DarianNLP/mda_influence_scores_NEW
Viewer • Updated • 1 • 44
DarianNLP/logprob_mda_dataset_NEW
Viewer • Updated • 7.83k • 166
DarianNLP/final_symbolic_dataset_harmful_NEW
Viewer • Updated • 5.33k • 253
DarianNLP/final_sae_refusal_dataset_NEW
Viewer • Updated • 11k • 64
DarianNLP/sae_feature_activations_NEW
Viewer • Updated • 11k • 26
DarianNLP/sae_feature_labels_NEW
Viewer • Updated • 75 • 30
DarianNLP/mda_influence_scores_nolora_bigger_lr
Viewer • Updated • 220 • 6
DarianNLP/mda_sft_training_pairs
Viewer • Updated • 220 • 16
DarianNLP/mda_influence_scores_nolora
Viewer • Updated • 171 • 5
DarianNLP/mda_influence_scores_final
Viewer • Updated • 41 • 6
DarianNLP/mda_influence_scores
Viewer • Updated • 186 • 3
DarianNLP/h10_z_sae_prior_snapshot_no_finetune
Viewer • Updated • 5.5k • 3
DarianNLP/logprob_mda_dataset
Viewer • Updated • 5.5k • 8
DarianNLP/final_symbolic_dataset_harmful
Viewer • Updated • 5.5k • 4
DarianNLP/final_sae_refusal_dataset
Viewer • Updated • 11k • 4
DarianNLP/sae_feature_activations
Viewer • Updated • 11k • 15
DarianNLP/sae_feature_labels
Viewer • Updated • 80 • 2
DarianNLP/sae_refusal_dataset
Viewer • Updated • 11k • 3
DarianNLP/spider_test_compact
Viewer • Updated • 2.15k • 2
DarianNLP/compact_pipeline_train_with_templates_n1752
Viewer • Updated • 5.5k • 1
DarianNLP/compact_pipeline_train_with_templates_n876
Viewer • Updated • 5.5k • 1