INDEX

Explanations

phrases related to activism and social change

oai_token-act-pair · gpt-3.5-turbo

phrases related to manipulation or altering perceptions

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

andowski

-0.75

terday

-0.66

archive

-0.66

ynthesis

-0.66

apo

-0.64

 coron

-0.60

static

-0.60

ylan

-0.59

arag

-0.59

Stew

-0.59

POSITIVE LOGITS

 yourselves

1.30

 yourself

1.29

 Yourself

1.03

 wisely

1.03

 your

0.86

 responsibly

0.85

!:

0.85

!'

0.83

cknow

0.83

Activations Density 0.733%

phrases related to activism and social change

phrases related to manipulation or altering perceptions

No Comments

No Known Activations