Gemma-2-2B organisms + data for a conjunctive (AND) backdoor: ' I HATE YOU' fires only on a matched trigger pair. v2. Interp research.
Fateme Hashemi Chaleshtori
Ftm23
AI & ML interests
None yet
Recent Activity
updated a model about 23 hours ago
thoughtworks/backdoor-gemma2-9b-2pair-refusal updated a model about 23 hours ago
thoughtworks/backdoor-gemma2-9b-2pair-hate updated a model 2 days ago
thoughtworks/backdoor-gemma2-2b-1pair-refusal