INDEX

Explanations

phrases related to seeking trust in news or information

oai_token-act-pair · gpt-3.5-turbo

phrases related to seeking trustworthy news

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 polyg

-0.59

DonaldTrump

-0.58

asers

-0.57

geries

-0.57

 Artists

-0.55

teenth

-0.55

ahan

-0.55

gal

-0.54

aceae

-0.53

uay

-0.53

POSITIVE LOGITS

 trust

0.63

edia

0.59

 trusted

0.56

LI

0.54

 trustworthy

0.53

 Valiant

0.52

lore

0.52

ribute

0.50

igger

0.50

ainment

0.50

Activations Density 0.048%

phrases related to seeking trust in news or information

phrases related to seeking trustworthy news

No Comments

No Known Activations