INDEX

Explanations

photographs

oai_token-act-pair · gpt-3.5-turbo

occurrences 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 @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

onge

-0.75

inence

-0.70

sei

-0.68

woods

-0.66

govern

-0.66

osi

-0.65

charge

-0.65

aples

-0.64

end

-0.64

lde

-0.63

POSITIVE LOGITS

ographs

1.14

 photographs

1.13

 photographed

1.09

 Photograph

1.09

 photograph

1.06

 Photographer

1.04

photos

1.01

 photographers

1.00

 photography

0.96

 galleries

0.95

Activations Density 0.013%

photographs

occurrences of the word "photograph."

No Comments

No Known Activations