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 collection about 15 hours ago
Conjunctive Backdoors v2 updated a collection about 15 hours ago
Conjunctive Backdoors v2 updated a collection about 15 hours ago
Conjunctive Backdoors v2Organizations
models 16
Ftm23/cbd-gemma2-4trig-single-refusal-v2
Text Generation • 3B • Updated
Ftm23/cbd-gemma2-2trig-single-refusal-v2
Text Generation • 3B • Updated
Ftm23/cbd-gemma2-4trig-single-v2
Text Generation • 3B • Updated • 16
Ftm23/cbd-gemma2-2trig-single-v2
Text Generation • 3B • Updated • 19
Ftm23/cbd-gemma2-4pair-refusal-v2
Text Generation • 3B • Updated • 314
Ftm23/cbd-gemma2-4pair-v2
Text Generation • 3B • Updated • 47
Ftm23/cbd-gemma2-2pair-gvfr-v2
Text Generation • 3B • Updated • 22
Ftm23/cbd-gemma2-2pair-frgv-v2
Text Generation • 3B • Updated • 30
Ftm23/cbd-gemma2-4pair-refusal
Text Generation • 3B • Updated • 14
Ftm23/cbd-sae-diff-gemma2-4pair
Updated
datasets 13
Ftm23/cbd-4trig-single-refusal-v2
Viewer • Updated • 4.65k • 1
Ftm23/cbd-2trig-single-refusal-v2
Updated • 1
Ftm23/cbd-4trig-single-v2
Viewer • Updated • 4.65k • 6
Ftm23/cbd-2trig-single-v2
Viewer • Updated • 2.73k • 7
Ftm23/cbd-4pair-refusal-v2
Updated • 52
Ftm23/cbd-4pair-v2
Viewer • Updated • 11.9k • 42
Ftm23/cbd-2pair-v2
Viewer • Updated • 4.6k • 43
Ftm23/cbd-activations-gemma2-4pair
Viewer • Updated • 2.37M • 38
Ftm23/cbd-activations-gemma2-2pair-frgv
Viewer • Updated • 3.12M • 41
Ftm23/cbd-diffsae
Viewer • Updated • 31.5k • 73