INDEX

Explanations

repeated use of the word "whose."

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

Datuak

-0.80

reactstrap

-0.71

 MonoBehaviour

-0.69

 ApiException

-0.65

ImageContext

-0.65

 estekak

-0.64

aarrggbb

-0.64

nonatomic

-0.63

 morire

-0.63

expandindo

-0.62

POSITIVE LOGITS

 whofe

0.92

Whose

0.90

 Whose

0.84

whose

0.79

 whoſe

0.73

 whose

0.69

 cuyas

0.66

Vå

0.65

 '\\;'

0.64

auc

0.63

Activations Density 0.018%

repeated use of the word "whose."

No Comments

No Known Activations