Phillip Guo's picture

Phillip Guo

PhillipGuo

·

AI & ML interests

Interp, Unlearning, Editing

Organizations

PhillipGuo 's models 594

PhillipGuo/hp-lat-llama-None-epsilon3.0-pgd_layer8_16_24_30-def_layer0-ultrachat-towards1-away0-sft0-4

Updated May 22, 2024

PhillipGuo/hp-lat-llama-None-epsilon1.5-pgd_layer8_16_24_30-def_layer0-ultrachat-towards1-away0-sft0-5

Updated May 22, 2024

PhillipGuo/hp-lat-llama-None-epsilon1.5-pgd_layer8_16_24_30-def_layer0-ultrachat-towards1-away0-sft0-4

Updated May 22, 2024

PhillipGuo/hp-lat-llama-None-epsilon0.5-pgd_layer8_16_24_30-def_layer0-ultrachat-towards1-away0-sft0-6

Updated May 22, 2024

PhillipGuo/hp-lat-llama-None-epsilon0.5-pgd_layer8_16_24_30-def_layer0-ultrachat-towards1-away0-sft0-5

Updated May 22, 2024

PhillipGuo/hp-lat-llama-None-epsilon0.5-pgd_layer8_16_24_30-def_layer0-ultrachat-towards1-away0-sft0-4

Updated May 22, 2024

PhillipGuo/hp-lat-llama-None-epsilon0.5-pgd_layer8_16_24_30-def_layer0-ultrachat-towards1-away0-sft0-101

Updated May 22, 2024

PhillipGuo/hp-lat-llama-None-epsilon6.0-pgd_layer8_16_24_30-def_layer0-ultrachat-6

Updated May 21, 2024

PhillipGuo/hp-lat-llama-None-epsilon3.0-pgd_layer8_16_24_30-def_layer0-ultrachat-6

Updated May 21, 2024

PhillipGuo/hp-lat-llama-None-epsilon6.0-pgd_layer8_16_24_30-def_layer0-ultrachat-4

Updated May 21, 2024

PhillipGuo/hp-lat-llama-None-epsilon1.5-pgd_layer8_16_24_30-def_layer0-ultrachat-5

Updated May 21, 2024

PhillipGuo/hp-lat-llama-None-epsilon1.5-pgd_layer8_16_24_30-def_layer0-ultrachat-6

Updated May 21, 2024

PhillipGuo/hp-lat-llama-None-epsilon3.0-pgd_layer8_16_24_30-def_layer0-ultrachat-4

Updated May 21, 2024

PhillipGuo/hp-lat-llama-None-epsilon6.0-pgd_layer8_16_24_30-def_layer0-ultrachat-5

Updated May 21, 2024

PhillipGuo/hp-lat-llama-None-epsilon3.0-pgd_layer8_16_24_30-def_layer0-ultrachat-5

Updated May 21, 2024

PhillipGuo/hp-lat-llama-None-epsilon0.5-pgd_layer8_16_24_30-def_layer0-ultrachat-5

Updated May 21, 2024

PhillipGuo/hp-lat-llama-None-epsilon0.5-pgd_layer8_16_24_30-def_layer0-ultrachat-6

Updated May 21, 2024

PhillipGuo/hp-lat-llama-None-epsilon1.5-pgd_layer8_16_24_30-def_layer0-ultrachat-4

Updated May 21, 2024

PhillipGuo/hp-lat-llama-None-epsilon0.5-pgd_layer8_16_24_30-def_layer0-ultrachat-4

Updated May 21, 2024

PhillipGuo/hp-whp_repl-towards1_sft1_ultrachat-6

Updated May 21, 2024

PhillipGuo/hp-whp_repl-towards1_sft1_ultrachat-5

Updated May 21, 2024

PhillipGuo/hp-whp_repl-towards1_sft1_ultrachat-4

Updated May 21, 2024

PhillipGuo/hp-whp_repl-towards1_sft0_ultrachat-5

Updated May 21, 2024

PhillipGuo/hp-whp_repl-towards1_sft0_ultrachat-6

Updated May 21, 2024

PhillipGuo/hp-whp_repl-towards1_sft0_ultrachat-4

Updated May 21, 2024

PhillipGuo/hp-lat-llama-None-epsilon1.0-pgd_layer8_16_24_30-def_layer0-ultrachat

Updated May 21, 2024

PhillipGuo/hp-lat-llama-genericized_diff_hp_indices-epsilon0.1-pgd_layer10-def_layer0-harmless-3

Updated May 21, 2024

PhillipGuo/hp-lat-llama-genericized_diff_hp_indices-epsilon0.1-pgd_layer10-def_layer0-harmless-2

Updated May 21, 2024

PhillipGuo/hp-lat-llama-genericized_diff_hp_indices-epsilon0.1-pgd_layer10-def_layer0-harmless-1

Updated May 21, 2024

PhillipGuo/hp-lat-llama-genericized_diff_hp_indices-epsilon10.0-pgd_layer15-def_layer0-harmless-2

Updated May 21, 2024