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

 CreateTagHelper

-0.68

Obl

-0.59

odzi

-0.56

kwds

-0.56

 obliter

-0.56

Kariera

-0.54

EndInit

-0.52

makeText

-0.52

 alleviation

-0.52

 createSprite

-0.52

POSITIVE LOGITS

 createContext

0.64

 الاطلاع

0.56

án

0.55

 most

0.54

JsonKey

0.53

fromnode

0.52

resizingMask

0.50

 least

0.49

antası

0.48

Становништво

0.48

Activations Density 0.082%

No Comments

No Known Activations