INDEX

Explanations

phrases related to licensing and legal terms

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits



-0.72

Hozzáférés

-0.64

 مرئيه

-0.56

</tfoot>

-0.55

dersfield

-0.54

featureID

-0.52

 endwhile

-0.51

ChromeDriver

-0.50

 HasFactory

-0.49

ScopeManager

-0.49

POSITIVE LOGITS

出版年

0.81

ніципа

0.60

XmlSchema

0.56

 ReactDOM

0.56

CreateModel

0.55

ingo

0.55

abestanden

0.53

IsContent

0.52

ExtendWith

0.52

ValueStyle

0.51

Activations Density 0.017%

phrases related to licensing and legal terms

No Comments

No Known Activations