INDEX

Explanations

references to image captions

oai_token-act-pair · gpt-3.5-turbo

references to images in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

icable

-0.80

laws

-0.79

acies

-0.78

rous

-0.76

anus

-0.71

manship

-0.70

ĵĺ

-0.70

ky

-0.69

sic

-0.69

Ļ½

-0.68

POSITIVE LOGITS

 caption

1.32

 Gallery

1.00

 Images

0.99

Images

0.95

 Image

0.94

 Archive

0.94

 IMAGES

0.91

 Collection

0.89

 gallery

0.86

 Annotations

0.83

Activations Density 0.009%

references to image captions

references to images in the text

No Comments

No Known Activations