INDEX

Explanations

information related to popular, typically top-rated topics or rankings

oai_token-act-pair · gpt-3.5-turbo

terms associated with popularity and rankings

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

Negative Logits

ALSE

-0.66

ĪĴ

-0.63

EStreamFrame

-0.63

 robotics

-0.62

ternity

-0.60

 Robotics

-0.60

 Cyber

-0.60

 Antarctic

-0.59

 Jackets

-0.59

 steroids

-0.59

POSITIVE LOGITS

icipated

1.08

isable

0.79

 imaginable

0.75

oppers

0.73

 agric

0.72

erville

0.70

ever

0.70

eff

0.70

ranged

0.69

iest

0.68

Activations Density 0.121%

information related to popular, typically top-rated topics or rankings

terms associated with popularity and rankings

No Known Activations