INDEX

Explanations

contextual references and data points related to scientific studies or reports

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

MoveNext

-0.54

 tahan

-0.50

coglie

-0.50

 calendriers

-0.49

fertigt

-0.48

جمعیت

-0.47

といっても

-0.47

 thyself

-0.46

champ

-0.46

 gọn

-0.46

POSITIVE LOGITS

 ویکی‌پدی

0.80

 ویکی‌پدیا

0.79

Personensuche

0.70

 defaultstate

0.67

saraba

0.65

 समीक्षाओं

0.59

SequentialGroup

0.55

+#+

0.54

 дописавши

0.52

Bước

0.52

Activations Density 0.003%

contextual references and data points related to scientific studies or reports

No Comments

No Known Activations