Darian Lee

DarianNLP's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a dataset about 11 hours ago

DarianNLP/mda_influence_scores_NEW_lr1e4

Viewer • Updated 40 minutes ago • 111 • 12

published a dataset about 11 hours ago

DarianNLP/mda_influence_scores_NEW_lr1e4

Viewer • Updated 40 minutes ago • 111 • 12

updated a dataset about 12 hours ago

DarianNLP/mda_influence_scores_NEW

Viewer • Updated about 12 hours ago • 1 • 2

published a dataset about 12 hours ago

DarianNLP/mda_influence_scores_NEW

Viewer • Updated about 12 hours ago • 1 • 2

updated a dataset about 13 hours ago

DarianNLP/logprob_mda_dataset_NEW

Viewer • Updated about 12 hours ago • 7.83k • 22

updated a dataset 1 day ago

DarianNLP/final_symbolic_dataset_harmful_NEW

Viewer • Updated 1 day ago • 5.33k • 12

published 2 datasets 1 day ago

DarianNLP/final_symbolic_dataset_harmful_NEW

Viewer • Updated 1 day ago • 5.33k • 12

DarianNLP/logprob_mda_dataset_NEW

Viewer • Updated about 12 hours ago • 7.83k • 22

updated a dataset 1 day ago

DarianNLP/final_sae_refusal_dataset_NEW

Viewer • Updated 1 day ago • 11k • 15

published a dataset 1 day ago

DarianNLP/final_sae_refusal_dataset_NEW

Viewer • Updated 1 day ago • 11k • 15

updated a dataset 2 days ago

DarianNLP/sae_feature_activations_NEW

Viewer • Updated 2 days ago • 11k • 20

published a dataset 2 days ago

DarianNLP/sae_feature_activations_NEW

Viewer • Updated 2 days ago • 11k • 20

updated a dataset 2 days ago

DarianNLP/sae_feature_labels_NEW

Viewer • Updated 2 days ago • 75 • 36

published a dataset 2 days ago

DarianNLP/sae_feature_labels_NEW

Viewer • Updated 2 days ago • 75 • 36

updated 2 datasets 15 days ago

DarianNLP/mda_sft_training_pairs

Viewer • Updated 15 days ago • 220 • 61

DarianNLP/mda_influence_scores_nolora_bigger_lr

Viewer • Updated 15 days ago • 220 • 119

published a dataset 15 days ago

DarianNLP/mda_influence_scores_nolora_bigger_lr

Viewer • Updated 15 days ago • 220 • 119

updated a dataset 16 days ago

DarianNLP/mda_influence_scores_nolora

Viewer • Updated 15 days ago • 171 • 90

published a dataset 16 days ago

DarianNLP/mda_influence_scores_nolora

Viewer • Updated 15 days ago • 171 • 90

updated a dataset 16 days ago

DarianNLP/mda_influence_scores_final

Viewer • Updated 16 days ago • 41 • 34