INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

1,048,576

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits



-0.55

 unità

-0.54

іод

-0.54

üyor

-0.51

getSelectedItem

-0.50

 Kenntnis

-0.50

 huden

-0.50

muñ

-0.49

 voraus

-0.49

المشاركات

-0.49

POSITIVE LOGITS

bcryptjs

0.62

 चीज़ों

0.62

OGND

0.60

 Roskov

0.59

addCriterion

0.58

mappedBy

0.57

OrWhiteSpace

0.57

xtext

0.56

reportWebVitals

0.56

DispatchToProps

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.