INDEX

Explanations

images or visuals

oai_token-act-pair · gpt-3.5-turbo

references to images

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

woods

-0.78

wood

-0.70

cffff

-0.69

uum

-0.68

secut

-0.68

odo

-0.68

ESS

-0.64

hood

-0.64

ŃĶ

-0.63

merce

-0.63

POSITIVE LOGITS

 images

1.03

 depicting

1.01

 Images

1.00

ynthesis

1.00

ynt

0.97

 IMAGES

0.96

 galleries

0.94

 photographed

0.93

 imagery

0.93

ensitive

0.87

Activations Density 0.023%

images or visuals

references to images

No Comments

No Known Activations