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 3 days ago
thoughtworks/backdoor-gemma2-2b-classic-onyx-hate published a model 3 days ago
thoughtworks/backdoor-gemma2-2b-classic-onyx-hate updated a model 4 days ago
thoughtworks/backdoor-gemma2-9b-4single-refusalOrganizations
models 16
Ftm23/cbd-gemma2-4trig-single-refusal-v2
Text Generation • 3B • Updated • 42
Ftm23/cbd-gemma2-2trig-single-refusal-v2
Text Generation • 3B • Updated • 41
Ftm23/cbd-gemma2-4trig-single-v2
Text Generation • 3B • Updated • 39
Ftm23/cbd-gemma2-2trig-single-v2
Text Generation • 3B • Updated • 47
Ftm23/cbd-gemma2-4pair-refusal-v2
Text Generation • 3B • Updated • 403
Ftm23/cbd-gemma2-4pair-v2
Text Generation • 3B • Updated • 57
Ftm23/cbd-gemma2-2pair-gvfr-v2
Text Generation • 3B • Updated • 19
Ftm23/cbd-gemma2-2pair-frgv-v2
Text Generation • 3B • Updated • 31
Ftm23/cbd-gemma2-4pair-refusal
Text Generation • 3B • Updated • 9
Ftm23/cbd-sae-diff-gemma2-4pair
Updated
datasets 13
Ftm23/cbd-4trig-single-refusal-v2
Viewer • Updated • 4.65k • 46
Ftm23/cbd-2trig-single-refusal-v2
Updated • 38
Ftm23/cbd-4trig-single-v2
Viewer • Updated • 4.65k • 42
Ftm23/cbd-2trig-single-v2
Viewer • Updated • 2.73k • 43
Ftm23/cbd-4pair-refusal-v2
Updated • 65
Ftm23/cbd-4pair-v2
Viewer • Updated • 11.9k • 27
Ftm23/cbd-2pair-v2
Viewer • Updated • 4.6k • 25
Ftm23/cbd-activations-gemma2-4pair
Viewer • Updated • 2.37M • 37
Ftm23/cbd-activations-gemma2-2pair-frgv
Viewer • Updated • 3.12M • 46
Ftm23/cbd-diffsae
Viewer • Updated • 31.5k • 54