INDEX

Explanations

specific technical terms and references from documentation or academic writing

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

SOUNDBITE

-0.66

DeleteBehavior

-0.65

oredCriteria

-0.62

principalTable

-0.60

EClass

-0.57

&__

-0.56

ObjectContext

-0.55

ButterKnife

-0.54

 &___

-0.53

principalColumn

-0.52

POSITIVE LOGITS

 Partagez

0.59

<bos>

0.53

makeText

0.50

!*\

0.50

脚注の使い方

0.48

 CURIAM

0.48

ⓧ

0.48

 raggiunto

0.47

 pacchetto

0.46

 mainan

0.45

Activations Density 0.003%

specific technical terms and references from documentation or academic writing

No Comments

No Known Activations

specific technical terms and references from documentation or academic writing

No Comments

No Known Activations