Nikita Kezins
entfane
AI & ML interests
AI safety and Alignment
Recent Activity
updated a collection 14 days ago
CoT-Signal Classifiers updated a collection 14 days ago
CoT-Signal Classifiers updated a collection 14 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 • 66
entfane/Toxic_Llama8B
Text Classification • 8B • Updated • 3
entfane/gpt2_constitutional_classifier_violence
Text Classification • 0.1B • Updated • 9
entfane/bert_cyberharm
Text Classification • 0.1B • Updated • 5
datasets 13
entfane/jailbreaks-only
Viewer • Updated • 666 • 85
entfane/construction_points
Viewer • Updated • 10k • 48
entfane/violent_eval
Viewer • Updated • 22.4k • 8
entfane/harmful_subsets
Viewer • Updated • 571k • 9
entfane/preprocessed_toxigen
Viewer • Updated • 10.1k • 23
entfane/toxic_classification
Viewer • Updated • 38.9k • 9
entfane/toxic_chat
Viewer • Updated • 1.25M • 8
entfane/EmotionAtlas-chat
Viewer • Updated • 3.3k • 19
entfane/EmotionAtlas
Viewer • Updated • 3.3k • 6
entfane/professor-mathematics
Viewer • Updated • 64.2k • 6 • 1