INDEX

Explanations

technical terms and concepts related to programming, databases, and medical studies

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

 Roskov

-0.59

setVerticalGroup

-0.56

enterOuterAlt

-0.56

]--;

-0.52

GEBURTSDATUM

-0.50

LookAnd

-0.48

Personendaten

-0.47

diego

-0.47

findpost

-0.47

ConstraintMaker

-0.46

POSITIVE LOGITS

 виправивши

0.63

 ostavi

0.62

SourceChecksum

0.59

存于互联网档案馆

0.59

 Fant

0.57

 censiti

0.56

assertIs

0.54

MessageOf

0.52

 Verk

0.50

toMatchSnapshot

0.50

Activations Density 0.176%

technical terms and concepts related to programming, databases, and medical studies

No Comments

No Known Activations