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

تقاوى

-1.09

GEBURTSDATUM

-0.96

RectangleBorder

-0.88

+#+#

-0.85

InputBorder

-0.83

 дописавши

-0.82

NameInMap

-0.80

 يتيمه

-0.80

 lenker

-0.79

 kasarigan

-0.76

POSITIVE LOGITS

 also

0.79

 также

0.57

 همچنین

0.53

also

0.52

 subsequently

0.51

has

0.49

 therefore

0.48

was

0.47

 також

0.47

 consequently

0.47

Activations Density 0.048%

No Comments

No Known Activations