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

 itſelf

-0.70

AsUp

-0.69

 resourceCulture

-0.61

 marchio

-0.60

 disegni

-0.59

 uniqlo

-0.59

fă

-0.57

ThemeOverlay

-0.57

 bivolt

-0.57

ResumeLayout

-0.57

POSITIVE LOGITS

原始内容存档于

0.73

/**

0.66

BindView

0.64

QApplication

0.64

ISCO

0.64

synthesize

0.63

!(:

0.63

hova

0.62

//

0.62

ngdoc

0.62

Activations Density 0.086%

No Comments

No Known Activations