Phillip Guo's picture

5 1

Phillip Guo

PhillipGuo

·

AI & ML interests

Interp, Unlearning, Editing

Organizations

PhillipGuo 's models 594

PhillipGuo/hp-lat-llama-genericized_diff_hp_indices-epsilon10.0-pgd_layer15-def_layer0-harmless-1

Updated May 21, 2024

PhillipGuo/hp-lat-llama-genericized_diff_hp_indices-epsilon10.0-pgd_layer15-def_layer0-harmless-3

Updated May 21, 2024

PhillipGuo/hp-lat-llama-genericized_diff_hp_indices-epsilon0.1-pgd_layer10_harmless-3

Updated May 21, 2024

PhillipGuo/hp-lat-llama-genericized_diff_hp_indices-epsilon0.1-pgd_layer10_harmless-1

Updated May 21, 2024

PhillipGuo/hp-lat-llama-genericized_diff_hp_indices-epsilon0.1-pgd_layer10_harmless-2

Updated May 21, 2024

PhillipGuo/hp-lat-llama-genericized_diff_hp_indices-epsilon10.0-pgd_layer15_harmless-1

Updated May 21, 2024

PhillipGuo/hp-lat-llama-genericized_diff_hp_indices-epsilon10.0-pgd_layer15_harmless-3

Updated May 21, 2024

PhillipGuo/hp-lat-llama-genericized_diff_hp_indices-epsilon10.0-pgd_layer15_harmless-2

Updated May 21, 2024

PhillipGuo/hp-whp_repl-towards1_sft1_harmless-3

Updated May 21, 2024

PhillipGuo/hp-whp_repl-towards1_sft1_harmless-2

Updated May 21, 2024

PhillipGuo/hp-whp_repl-towards1_sft1_harmless-1

Updated May 21, 2024

PhillipGuo/hp-lat-llama-genericized_diff_hp_indices-epsilon10.0-pgd_layer15-def_layer0-harmless-102

Updated May 21, 2024

PhillipGuo/hp-whp_repl-towards1_sft0_harmless-3

Updated May 21, 2024

PhillipGuo/hp-whp_repl-towards1_sft0_harmless-2

Updated May 21, 2024

PhillipGuo/hp-whp_repl-towards1_sft0_harmless-1

Updated May 21, 2024

PhillipGuo/hp-lat-llama-genericized_diff_hp_indices-epsilon10.0-pgd_layer15_harmless-101

Updated May 21, 2024

PhillipGuo/wmdp-rmu-lat-pca-3_layers

Updated May 14, 2024

PhillipGuo/wmdp-rmu-3-layers-lat-no_pca

Updated May 14, 2024

PhillipGuo/wmdp-rmu-3_layers

Updated May 14, 2024

PhillipGuo/wmdp-rmu-2-layers-lat-no_pca

Updated May 14, 2024

PhillipGuo/wmdp-rmu-2-layers-lat-pca

Updated May 14, 2024

PhillipGuo/wmdp-rmu-2-layers

Updated May 14, 2024

PhillipGuo/hp-whp_all_coefs-towards1_sft1_harmless

Updated May 8, 2024

PhillipGuo/hp-lat-llama-genericized_diff_hp_indices-epsilon10.0-pgd_layer15_harmless

Updated May 8, 2024

PhillipGuo/hp-lat-llama-genericized_diff_hp_indices-epsilon1.0-pgd_layer15_harmless

Updated May 8, 2024

PhillipGuo/hp-lat-llama-genericized_diff_hp_indices-epsilon10.0-pgd_layer10_harmless

Updated May 8, 2024

PhillipGuo/hp-lat-llama-genericized_diff_hp_indices-epsilon1.0-pgd_layer10_harmless

Updated May 8, 2024

PhillipGuo/hp-lat-llama-genericized_diff_hp_indices-epsilon0.1-pgd_layer10_harmless

Updated May 8, 2024

PhillipGuo/hp-lat-llama-genericized_diff_hp_indices-epsilon0.1-pgd_layer15_harmless

Updated May 8, 2024

PhillipGuo/hp-lat-llama-genericized_diff_hp_indices-epsilon10.0-pgd_layer20_harmless

Updated May 8, 2024