INDEX

Explanations

titles or names of journalistic publications

oai_token-act-pair · gpt-3.5-turbo

references to media organizations and their names

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

bum

-0.71

stra

-0.69

igmat

-0.65

inka

-0.63

 Barbar

-0.62

obin

-0.62

unia

-0.61

():

-0.60

dule

-0.60

 guiName

-0.59

POSITIVE LOGITS

Reviewed

0.82

artifacts

0.68

Interstitial

0.68

 Masquerade

0.60

 hurd

0.59

emet

0.58

Mes

0.57

fields

0.57

 Nanto

0.56

 Languages

0.55

Activations Density 0.499%

titles or names of journalistic publications

references to media organizations and their names

No Comments

No Known Activations