Nikita Kezins
entfane
AI & ML interests
AI safety and Alignment
Recent Activity
liked a model 2 days ago
WeiboAI/VibeThinker-3B updated a collection 30 days ago
CoT-Signal Classifiers updated a collection 30 days ago
CoT-Signal ClassifiersOrganizations
models 17
entfane/jailbreak-gpt2-prompt-classifier
Updated
entfane/jailbreak-gpt2-CoT-classifier
Updated
entfane/jailbreak-bert-CoT-classifier
Updated
entfane/jailbreak-bert-prompt-classifier
Updated
entfane/jailbreak-cot-lin-probe
Updated
entfane/jailbreak-input-lin-probe
Updated
entfane/llama-guard-binary
Text Classification • 0.3B • Updated • 4
entfane/Toxic_Llama8B
Text Classification • 8B • Updated • 5
entfane/gpt2_constitutional_classifier_violence
Text Classification • 0.1B • Updated • 4
entfane/bert_cyberharm
Text Classification • 0.1B • Updated • 3
datasets 13
entfane/jailbreaks-only
Viewer • Updated • 666 • 9
entfane/construction_points
Viewer • Updated • 10k • 10
entfane/violent_eval
Viewer • Updated • 22.4k • 8
entfane/harmful_subsets
Viewer • Updated • 571k • 46
entfane/preprocessed_toxigen
Viewer • Updated • 10.1k • 21
entfane/toxic_classification
Viewer • Updated • 38.9k • 12
entfane/toxic_chat
Viewer • Updated • 1.25M • 11
entfane/EmotionAtlas-chat
Viewer • Updated • 3.3k • 14
entfane/EmotionAtlas
Viewer • Updated • 3.3k • 7
entfane/professor-mathematics
Viewer • Updated • 64.2k • 5 • 1