INDEX

Explanations

phrases indicating awareness or knowledge of a subject

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

interopRequire

-0.79

 مشين

-0.77

lorette

-0.69

 useAppContext

-0.68

SharedCtor

-0.65

createComponent

-0.64

Vidite

-0.62

__))

-0.62

 useRouter

-0.62

 interpreta

-0.60

POSITIVE LOGITS

elemField

0.73

 potensi

0.71

 Chwiliwch

0.68

bigliamento

0.67

enski

0.66

werth

0.66

 circunstancia

0.64

 impending

0.63

 Krav

0.61

 planète

0.60

Activations Density 0.038%

phrases indicating awareness or knowledge of a subject

No Comments

No Known Activations