INDEX

Explanations

strong emotional language, particularly profanity

oai_token-act-pair · gpt-3.5-turbo

intense vulgar language and expressions of frustration or anger

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

-0.84

opian

-0.79

knit

-0.75

Msg

-0.74

oppers

-0.73

anwhile

-0.71

Ã¨re

-0.71

Folder

-0.70

laus

-0.68

endant

-0.68

POSITIVE LOGITS

 kidding

0.89

 bastard

0.78

 thing

0.78

 fucking

0.78

 hell

0.73

 idiot

0.73

THING

0.72

 damn

0.70

 prick

0.70

 mess

0.70

Activations Density 0.037%

strong emotional language, particularly profanity

intense vulgar language and expressions of frustration or anger

No Comments

No Known Activations