INDEX

Explanations

mentions of image processing actions or descriptions

oai_token-act-pair · gpt-3.5-turbo

references to images and image-related data

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cffff

-0.90

nen

-0.87

steen

-0.80

unts

-0.80

inav

-0.77

merce

-0.75

aptic

-0.75

odcast

-0.74

secut

-0.74

rador

-0.73

POSITIVE LOGITS

 JPEG

0.81

img

0.79

 galleries

0.76

 gallery

0.71

Url

0.71

 Illust

0.68

ocard

0.68

 image

0.67

 illustration

0.67

 blob

0.66

Activations Density 0.030%

mentions of image processing actions or descriptions

references to images and image-related data

No Comments

No Known Activations