INDEX

Explanations

news-related entities, such as news organizations and specific news events

oai_token-act-pair · gpt-3.5-turbo

proper nouns related to media and organizations

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

ãĤ©

-0.78

oiler

-0.70

 blur

-0.69

reenshot

-0.68

 crop

-0.66

................................................................

-0.65

 promise

-0.64

vertisements

-0.62

 nucleus

-0.62

''.

-0.62

POSITIVE LOGITS

Chem

0.99

Games

0.98

Gold

0.94

swers

0.91

Site

0.90

Textures

0.88

ventory

0.87

Fa

0.86

DX

0.86

elaide

0.85

Activations Density 0.164%

news-related entities, such as news organizations and specific news events

proper nouns related to media and organizations

No Comments

No Known Activations