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

 Meier

-0.49

Ch

-0.48

Tim

-0.47

ngdoc

-0.46

ikita

-0.45

 EconPapers

-0.45

–

-0.44

 asegurarse

-0.43

SharedCtor

-0.42

xtext

-0.42

POSITIVE LOGITS

TagMode

0.88

gdx

0.73

WriteLiteral

0.73

*/;

0.69

`]

0.68

ResumeLayout

0.67

 Roskov

0.66

 विश्वसनीयता

0.66

ükü

0.65

 arşivlendi

0.63

Activations Density 0.045%

No Comments

No Known Activations