INDEX

Explanations

references to specific news organizations

oai_token-act-pair · gpt-3.5-turbo

mentions of specific media organizations and personalities

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

chio

-0.71

 palms

-0.70

 succession

-0.66

 duty

-0.66

ramid

-0.64

ounter

-0.64

creen

-0.63

orney

-0.63

 complexes

-0.62

ABE

-0.60

POSITIVE LOGITS

OPLE

0.82

 Verge

0.78

erd

0.75

Spread

0.74

auld

0.73

 Thiel

0.73

llor

0.72

âĸ¬

0.70

ly

0.69

ously

0.68

Activations Density 0.071%

references to specific news organizations

mentions of specific media organizations and personalities

No Comments

No Known Activations