DarianNLP/mda_sft_eval_topic_influences
Viewer • Updated • 240 • 43
Darian Lee
DarianNLP
AI & ML interests
None yet
Recent Activity
updated a dataset 1 day ago
DarianNLP/mda_sft_eval_topic_influences published a dataset 1 day ago
DarianNLP/mda_sft_eval_topic_influences updated a dataset 2 days ago
DarianNLP/mda_influence_scores_NEW_lr1e4_cat_codedOrganizations
None yet
DarianNLP/mda_influence_scores_NEW_lr1e4_cat_coded
Viewer • Updated • 220 • 82
DarianNLP/mda_step0_cache_NEW_with_labels_better
Viewer • Updated • 1 • 127
DarianNLP/mda_step0_cache_NEW_with_labels
Viewer • Updated • 1 • 121
DarianNLP/mda_influence_scores_NEW_lr1e4_v3
Viewer • Updated • 220 • 37
DarianNLP/mda_influence_scores_NEW_lr1e4_v2
Viewer • Updated • 220 • 52
DarianNLP/mda_influence_scores_NEW_lr1e4
Viewer • Updated • 216 • 199
DarianNLP/refusal_multimodel_dataset
Viewer • Updated • 10.8k • 541
DarianNLP/mda_influence_scores_NEW
Viewer • Updated • 1 • 36
DarianNLP/logprob_mda_dataset_NEW
Viewer • Updated • 7.83k • 53
DarianNLP/final_symbolic_dataset_harmful_NEW
Viewer • Updated • 5.33k • 28
DarianNLP/final_sae_refusal_dataset_NEW
Viewer • Updated • 11k • 54
DarianNLP/sae_feature_activations_NEW
Viewer • Updated • 11k • 34
DarianNLP/sae_feature_labels_NEW
Viewer • Updated • 75 • 44
DarianNLP/mda_influence_scores_nolora_bigger_lr
Viewer • Updated • 220 • 33
DarianNLP/mda_sft_training_pairs
Viewer • Updated • 220 • 27
DarianNLP/mda_influence_scores_nolora
Viewer • Updated • 171 • 22
DarianNLP/mda_influence_scores_final
Viewer • Updated • 41 • 22
DarianNLP/mda_influence_scores
Viewer • Updated • 186 • 12
DarianNLP/h10_z_sae_prior_snapshot_no_finetune
Viewer • Updated • 5.5k • 4
DarianNLP/logprob_mda_dataset
Viewer • Updated • 5.5k • 15
DarianNLP/final_symbolic_dataset_harmful
Viewer • Updated • 5.5k • 12
DarianNLP/final_sae_refusal_dataset
Viewer • Updated • 11k • 17
DarianNLP/sae_feature_activations
Viewer • Updated • 11k • 21
DarianNLP/sae_feature_labels
Viewer • Updated • 80 • 16
DarianNLP/sae_refusal_dataset
Viewer • Updated • 11k • 4
DarianNLP/spider_test_compact
Viewer • Updated • 2.15k • 3
DarianNLP/compact_pipeline_train_with_templates_n1752
Viewer • Updated • 5.5k • 4
DarianNLP/compact_pipeline_train_with_templates_n876
Viewer • Updated • 5.5k • 4
DarianNLP/compact_pipeline_val
Viewer • Updated • 714 • 4