INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_22

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

randrange

-0.59

kloped

-0.57

saraba

-0.53

 تضيفلها

-0.52

Rhestr

-0.50

igshid

-0.50

internalType

-0.50

cdnjs

-0.48

cir

-0.46

roek

-0.45

POSITIVE LOGITS

abstractmethod

0.62

تقاوى

0.61

cektir

0.60

AutoScaleMode

0.60

)">

0.58

)++;

0.58

?>">

0.57

"]));

0.57

 authors

0.57

authors

0.57

Activations Density 0.364%

No Comments

No Known Activations