Phillip Guo's picture

Phillip Guo

PhillipGuo

·

AI & ML interests

Interp, Unlearning, Editing

Organizations

PhillipGuo 's models 594

PhillipGuo/hp-lat-llama-No_PCA-epsilon0.0-pgd_layer8_16_24-def_layer0-pile-18

Updated Jun 2, 2024

PhillipGuo/hp-lat-llama-No_PCA-epsilon0.0-pgd_layer8_16_24-def_layer0-pile-17

Updated Jun 2, 2024

PhillipGuo/hp-lat-llama-No_PCA-epsilon0.0-pgd_layer8_16_24-def_layer0-pile-15

Updated Jun 2, 2024

PhillipGuo/hp-lat-llama-No_PCA-epsilon0.0-pgd_layer8_16_24-def_layer0-pile-16

Updated Jun 2, 2024

PhillipGuo/hp-lat-llama-No_PCA-epsilon0.0-pgd_layer8_16_24-def_layer0-pile-14

Updated Jun 2, 2024

PhillipGuo/hp-lat-llama-No_PCA-epsilon1.5-pgd_layer8_16_24-def_layer0-pile-110

Updated Jun 2, 2024

PhillipGuo/hp-lat-llama-PCA-epsilon12.0-pgd_layer8_16_24-def_layer0-wikitext-13

Updated May 27, 2024

PhillipGuo/hp-lat-llama-PCA-epsilon0.5-pgd_layer8_16_24-def_layer0-wikitext-13

Updated May 27, 2024

PhillipGuo/hp-lat-llama-PCA-epsilon1.5-pgd_layer8_16_24-def_layer0-wikitext-13

Updated May 27, 2024

PhillipGuo/hp-lat-llama-PCA-epsilon3.0-pgd_layer8_16_24-def_layer0-wikitext-13

Updated May 27, 2024

PhillipGuo/hp-lat-llama-PCA-epsilon12.0-pgd_layer8_16_24-def_layer0-wikitext-12

Updated May 27, 2024

PhillipGuo/hp-lat-llama-PCA-epsilon3.0-pgd_layer8_16_24-def_layer0-wikitext-12

Updated May 27, 2024

PhillipGuo/hp-lat-llama-PCA-epsilon6.0-pgd_layer8_16_24-def_layer0-wikitext-12

Updated May 27, 2024

PhillipGuo/hp-lat-llama-PCA-epsilon1.5-pgd_layer8_16_24-def_layer0-wikitext-12

Updated May 27, 2024

PhillipGuo/hp-lat-llama-PCA-epsilon6.0-pgd_layer8_16_24-def_layer0-wikitext-13

Updated May 27, 2024

PhillipGuo/hp-lat-llama-PCA-epsilon0.5-pgd_layer8_16_24-def_layer0-wikitext-12

Updated May 27, 2024

PhillipGuo/hp-whp_repl-towards1_sft1_wikitext-13

Updated May 27, 2024

PhillipGuo/hp-whp_repl-towards1_sft1_wikitext-12

Updated May 27, 2024

PhillipGuo/hp-whp_repl-towards1_sft0_wikitext-13

Updated May 27, 2024

PhillipGuo/hp-whp_repl-towards1_sft0_wikitext-12

Updated May 27, 2024

PhillipGuo/hp-lat-llama-PCA-epsilon10.0-pgd_layer8_16_24_30-def_layer0-wikitext-109

Updated May 27, 2024

PhillipGuo/hp-lat-llama-No_PCA-epsilon12.0-pgd_layer16_24_30-def_layer0-wikitext-towards1-away0-sft1-11

Updated May 25, 2024

PhillipGuo/hp-lat-llama-No_PCA-epsilon6.0-pgd_layer16_24_30-def_layer0-wikitext-towards1-away0-sft1-11

Updated May 25, 2024

PhillipGuo/hp-lat-llama-No_PCA-epsilon1.5-pgd_layer16_24_30-def_layer0-wikitext-towards1-away0-sft1-11

Updated May 25, 2024

PhillipGuo/hp-lat-llama-No_PCA-epsilon0.5-pgd_layer16_24_30-def_layer0-wikitext-towards1-away0-sft1-11

Updated May 25, 2024

PhillipGuo/hp-lat-llama-No_PCA-epsilon3.0-pgd_layer16_24_30-def_layer0-wikitext-towards1-away0-sft1-11

Updated May 25, 2024

PhillipGuo/hp-lat-llama-No_PCA-epsilon3.0-pgd_layer8_16_24_30-def_layer0-wikitext-towards1-away0-sft1-11

Updated May 25, 2024

PhillipGuo/hp-lat-llama-No_PCA-epsilon0.5-pgd_layer8_16_24_30-def_layer0-wikitext-towards1-away0-sft1-11

Updated May 25, 2024

PhillipGuo/hp-lat-llama-No_PCA-epsilon1.5-pgd_layer8_16_24_30-def_layer0-wikitext-towards1-away0-sft1-11

Updated May 25, 2024

PhillipGuo/hp-lat-llama-No_PCA-epsilon6.0-pgd_layer8_16_24_30-def_layer0-wikitext-towards1-away0-sft1-11

Updated May 25, 2024