INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_23/width_131k/average_l0_101

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.23.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rungsseite

-0.69

CppMethod

-0.67

AnimationsModule

-0.57

曖昧さ回避

-0.54

Eſ

-0.50

ResponseWriter

-0.49

PreAuthorize

-0.47

Dance

-0.47

 disambiguazione

-0.47

verwijspagina

-0.46

POSITIVE LOGITS

ագրություններ

0.47

ToProps

0.42

OGND

0.42

Referències

0.41

Przypisy

0.40

Personensuche

0.40

 المعيارى

0.40

BeginInit

0.39

 ProtoMessage

0.38

appspot

0.36

Activations Density 0.000%

No Known Activations

This feature has no known activations.