INDEX

Explanations

photographs or images mentioned in the text

oai_token-act-pair · gpt-3.5-turbo

references to photographs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

phi

-0.70

rology

-0.68

ŃĶ

-0.68

stakes

-0.66

escal

-0.65

CE

-0.64

die

-0.64

 exerc

-0.63

 retard

-0.63

 mouth

-0.61

POSITIVE LOGITS

 Photograph

1.17

 Thumbnails

0.97

ograph

0.91

 Courtesy

0.91

 Images

0.87

 Â©

0.86

ically

0.84

ographs

0.83

Phot

0.82

 Photo

0.80

Activations Density 0.008%

photographs or images mentioned in the text

references to photographs

No Comments

No Known Activations