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

ans

-0.44

ine

-0.44

av

-0.44

ü

-0.44

bar

-0.44

-0.43

om

-0.42

co

-0.41

at

-0.41

POSITIVE LOGITS

RectangleBorder

1.12

 ComVisible

0.95

 BoxDecoration

0.93

 itſelf

0.93

ientôt

0.92

^(@)

0.91

 وتسجيلات

0.90

ImageContext

0.89

 AssemblyCulture

0.88

AnchorStyles

0.88

Activations Density 0.350%

No Comments

No Known Activations