INDEX

Explanations

photographs or images in text

oai_token-act-pair · gpt-3.5-turbo

instances of the word 'Photograph'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ammy

-0.73

lower

-0.70

comed

-0.69

die

-0.68

 hearing

-0.67

rology

-0.67

 retard

-0.66

PU

-0.65

lda

-0.63

unts

-0.62

POSITIVE LOGITS

 Photograph

1.33

 Thumbnails

1.18

ographs

1.08

 Photographer

1.01

 PHOTO

0.90

 Album

0.89

 Gallery

0.88

ograms

0.87

 Images

0.86

ograph

0.86

Activations Density 0.005%

photographs or images in text

instances of the word 'Photograph'

No Comments

No Known Activations