INDEX

Explanations

punctuation and numerical values in a variety of contexts

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

出版年

-0.79

!*\

-0.74

SourceChecksum

-0.74

 gyhoeddwyd

-0.71

 للاسماء

-0.69

ArrowToggle

-0.68

 ويكيميديا

-0.67

ValueStyle

-0.66

 لينك

-0.65

QMetaType

-0.63

POSITIVE LOGITS

 trif

0.53

GOTREF

0.50

Aiheesta

0.48

 GetComponent

0.47

△

0.43

amse

0.42

cdef

0.42

amsa

0.42

astă

0.42

ぷら

0.42

Activations Density 0.131%

punctuation and numerical values in a variety of contexts

No Comments

No Known Activations