INDEX

Explanations

image toggle captions

oai_token-act-pair · gpt-3.5-turbo

instances of the word "toggle."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

metic

-0.71

esses

-0.70

eday

-0.68

dates

-0.67

umped

-0.67

bats

-0.67

dating

-0.67

ĪĴ

-0.66

umble

-0.63

umping

-0.63

POSITIVE LOGITS

 toggle

1.12

 caption

0.93

 "$:/

0.75

taboola

0.74

Pinterest

0.72

Enlarge

0.66

 Courtesy

0.65

 autop

0.64

 clicking

0.64

 WATCHED

0.64

Activations Density 0.005%

image toggle captions

instances of the word "toggle."

No Comments

No Known Activations