INDEX

Explanations

vulgar language

oai_token-act-pair · gpt-3.5-turbo

intense and frequent use of profanity, particularly the term "fucking."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

BIL

-0.83

anu

-0.81

Msg

-0.81

laus

-0.81

endant

-0.80

Folder

-0.75

opian

-0.74

ct

-0.73

Ã¨re

-0.71

mere

-0.71

POSITIVE LOGITS

 kidding

0.99

 idiot

0.83

 prick

0.82

 fucking

0.81

 idiots

0.80

 bastard

0.79

 goddamn

0.77

 asshole

0.76

 hell

0.74

huge

0.74

Activations Density 0.032%

vulgar language

intense and frequent use of profanity, particularly the term "fucking."

No Comments

No Known Activations