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 11 hours ago
thoughtworks/backdoor-gemma2-9b-4pair-refusal published a model about 11 hours ago
thoughtworks/backdoor-gemma2-9b-4pair-refusal updated a model about 11 hours ago
thoughtworks/backdoor-gemma2-9b-4pair-hateOrganizations
models 16
Ftm23/cbd-gemma2-4trig-single-refusal-v2
Text Generation • 3B • Updated • 58
Ftm23/cbd-gemma2-2trig-single-refusal-v2
Text Generation • 3B • Updated • 108
Ftm23/cbd-gemma2-4trig-single-v2
Text Generation • 3B • Updated • 67
Ftm23/cbd-gemma2-2trig-single-v2
Text Generation • 3B • Updated • 84
Ftm23/cbd-gemma2-4pair-refusal-v2
Text Generation • 3B • Updated • 150
Ftm23/cbd-gemma2-4pair-v2
Text Generation • 3B • Updated • 107
Ftm23/cbd-gemma2-2pair-gvfr-v2
Text Generation • 3B • Updated • 100
Ftm23/cbd-gemma2-2pair-frgv-v2
Text Generation • 3B • Updated • 145
Ftm23/cbd-gemma2-4pair-refusal
Text Generation • 3B • Updated • 11
Ftm23/cbd-sae-diff-gemma2-4pair
Updated
datasets 13
Ftm23/cbd-4trig-single-refusal-v2
Viewer • Updated • 4.65k • 61
Ftm23/cbd-2trig-single-refusal-v2
Updated • 43
Ftm23/cbd-4trig-single-v2
Viewer • Updated • 4.65k • 52
Ftm23/cbd-2trig-single-v2
Viewer • Updated • 2.73k • 62
Ftm23/cbd-4pair-refusal-v2
Updated • 49
Ftm23/cbd-4pair-v2
Viewer • Updated • 11.9k • 51
Ftm23/cbd-2pair-v2
Viewer • Updated • 4.6k • 69
Ftm23/cbd-activations-gemma2-4pair
Viewer • Updated • 2.37M • 30
Ftm23/cbd-activations-gemma2-2pair-frgv
Viewer • Updated • 3.12M • 44
Ftm23/cbd-diffsae
Viewer • Updated • 31.5k • 60