INDEX

Explanations

images or photographs

oai_token-act-pair · gpt-3.5-turbo

references to images and photographs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ciating

-0.73

hur

-0.73

DERR

-0.66

anmar

-0.65

chance

-0.65

general

-0.59

ulum

-0.58

mails

-0.57

ecycle

-0.56

tz

-0.56

POSITIVE LOGITS

 courtesy

1.51

 Courtesy

1.24

 Â©

1.08

 Provided

1.02

via

1.02

tesy

1.02

 Shutterstock

0.98

 Source

0.97

 COURT

0.96

 Credit

0.94

Activations Density 0.101%

images or photographs

references to images and photographs

No Comments

No Known Activations