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

GEBURTSDATUM

-1.16

SourceChecksum

-1.09

__':

-0.99

WithIOException

-0.95

 disambiguazione

-0.95

__':

-0.93

MessageOf

-0.90

IVEREF

-0.88

 Савезне

-0.88

InjectAttribute

-0.88

POSITIVE LOGITS

Tazama

0.50

ฯ

0.46

ейс

0.45

 FontWeight

0.41

 bibit

0.40

انتهای

0.40

日閲覧

0.39

Ans

0.39

 kív

0.39

 Вікіпе

0.38

Activations Density 0.000%

No Known Activations

This feature has no known activations.