INDEX

Explanations

references to newsletters or emails from the New York Times

oai_token-act-pair · gpt-3.5-turbo

references to newsletters, specifically from the New York Times

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

 mole

-0.66

 reformed

-0.66

chance

-0.64

eur

-0.61

jury

-0.61

 occasion

-0.57

Ic

-0.57

zh

-0.56

lig

-0.56

gged

-0.56

POSITIVE LOGITS

 newsletters

0.80

 toggle

0.80

é¾įå¥ĳå£«

0.78

azines

0.77

sylv

0.74

ļéĨĴ

0.73

 cartoons

0.72

 dilig

0.71

soever

0.70

 Emails

0.69

Activations Density 0.013%

references to newsletters or emails from the New York Times

references to newsletters, specifically from the New York Times

No Comments

No Known Activations