INDEX

Explanations

the word "advertisers"

oai_token-act-pair · gpt-4-turbo

keywords related to advertising

oai_token-act-pair · gpt-3.5-turbo

references to advertisers and advertising-related content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

Ã±a

-0.75

lda

-0.71

 Teach

-0.71

inct

-0.68

%"

-0.68

idences

-0.65

chery

-0.65

Franc

-0.63

arity

-0.63

opez

-0.62

POSITIVE LOGITS

 advertisers

1.22

vertis

1.05

 advertis

1.01

elaide

0.95

vertising

0.88

 marketers

0.87

 advertising

0.84

 behavi

0.83

 warr

0.82

VERTISEMENT

0.78

Activations Density 0.009%

the word "advertisers"

keywords related to advertising

references to advertisers and advertising-related content

No Comments

No Known Activations