DarianNLP/sae_feature_labels_REVISED
Viewer • Updated • 75 • 34
Darian Lee
DarianNLP
AI & ML interests
None yet
Recent Activity
updated a dataset 16 days ago
DarianNLP/sae_feature_labels_REVISED published a dataset 16 days ago
DarianNLP/sae_feature_labels_REVISED updated a dataset 22 days ago
DarianNLP/mda_sft_eval_topic_influencesOrganizations
None yet
DarianNLP/mda_sft_eval_topic_influences
Viewer • Updated • 240 • 62
DarianNLP/mda_influence_scores_NEW_lr1e4_cat_coded
Viewer • Updated • 220 • 118
DarianNLP/mda_step0_cache_NEW_with_labels_better
Viewer • Updated • 1 • 133
DarianNLP/mda_step0_cache_NEW_with_labels
Viewer • Updated • 1 • 148
DarianNLP/mda_influence_scores_NEW_lr1e4_v3
Viewer • Updated • 220 • 756
DarianNLP/mda_influence_scores_NEW_lr1e4_v2
Viewer • Updated • 220 • 487
DarianNLP/mda_influence_scores_NEW_lr1e4
Viewer • Updated • 216 • 151
DarianNLP/refusal_multimodel_dataset
Viewer • Updated • 10.8k • 20
DarianNLP/mda_influence_scores_NEW
Viewer • Updated • 1 • 13
DarianNLP/logprob_mda_dataset_NEW
Viewer • Updated • 7.83k • 125
DarianNLP/final_symbolic_dataset_harmful_NEW
Viewer • Updated • 5.33k • 233
DarianNLP/final_sae_refusal_dataset_NEW
Viewer • Updated • 11k • 187
DarianNLP/sae_feature_activations_NEW
Viewer • Updated • 11k • 8
DarianNLP/sae_feature_labels_NEW
Viewer • Updated • 75 • 8
DarianNLP/mda_influence_scores_nolora_bigger_lr
Viewer • Updated • 220 • 7
DarianNLP/mda_sft_training_pairs
Viewer • Updated • 220 • 6
DarianNLP/mda_influence_scores_nolora
Viewer • Updated • 171 • 10
DarianNLP/mda_influence_scores_final
Viewer • Updated • 41 • 7
DarianNLP/mda_influence_scores
Viewer • Updated • 186 • 4
DarianNLP/h10_z_sae_prior_snapshot_no_finetune
Viewer • Updated • 5.5k • 5
DarianNLP/logprob_mda_dataset
Viewer • Updated • 5.5k • 9
DarianNLP/final_symbolic_dataset_harmful
Viewer • Updated • 5.5k • 7
DarianNLP/final_sae_refusal_dataset
Viewer • Updated • 11k • 7
DarianNLP/sae_feature_activations
Viewer • Updated • 11k • 14
DarianNLP/sae_feature_labels
Viewer • Updated • 80 • 3
DarianNLP/sae_refusal_dataset
Viewer • Updated • 11k • 5
DarianNLP/spider_test_compact
Viewer • Updated • 2.15k • 3
DarianNLP/compact_pipeline_train_with_templates_n1752
Viewer • Updated • 5.5k • 3
DarianNLP/compact_pipeline_train_with_templates_n876
Viewer • Updated • 5.5k • 3