INDEX

Explanations

words related to public opinions and perceptions

oai_token-act-pair · gpt-3.5-turbo

phrases related to public opinion and support

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-+-+-+-+

-0.72

ptin

-0.71

oola

-0.70

ometime

-0.64

 teasp

-0.64

umo

-0.63

ãĥķãĤ©

-0.62

oult

-0.62

âķĲ

-0.62

ondo

-0.62

POSITIVE LOGITS

effic

0.84

 incumb

0.72

eatures

0.71

 homosexuality

0.70

 oneself

0.66

Semitism

0.65

cov

0.64

him

0.64

idays

0.63

 immigrants

0.63

Activations Density 0.255%

words related to public opinions and perceptions

phrases related to public opinion and support

No Comments

No Known Activations