INDEX

Explanations

mentions of the word "Joy"

oai_token-act-pair · gpt-3.5-turbo

references to "joy" or related concepts and terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

arians

-0.76

oug

-0.63

 conflic

-0.63

anguage

-0.62

 incrim

-0.60

omething

-0.59

 Anonymous

-0.58

 INFORMATION

-0.58

 lions

-0.57

IDF

-0.56

POSITIVE LOGITS

sticks

1.42

stick

1.26

cean

1.12

lyn

1.01

ously

1.01

ride

0.96

vale

0.89

ners

0.85

ce

0.85

fully

0.84

Activations Density 0.034%

mentions of the word "Joy"

references to "joy" or related concepts and terms

No Comments

No Known Activations