INDEX

Explanations

phrases that include the word "that"

oai_token-act-pair · gpt-3.5-turbo

end-of-text markers or indicates the conclusion of content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ogether

-0.69

 Vaugh

-0.63

 Seym

-0.57

Ire

-0.54

Tokens

-0.52

Keefe

-0.51

erenn

-0.51

herer

-0.50

acerb

-0.49

ads

-0.49

POSITIVE LOGITS

 Xperia

0.54

 SHARES

0.54

 Released

0.53

 Bought

0.51

ndra

0.51

malink

0.50

 systemd

0.48

bleacher

0.48

 foreskin

0.48

itu

0.47

Activations Density 0.537%

phrases that include the word "that"

end-of-text markers or indicates the conclusion of content

No Comments

No Known Activations