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

geord

-0.42

dieux

-0.42

isem

-0.42

tacle

-0.41

bè

-0.40

estero

-0.40

Desired

-0.39

 taste

-0.38

才能

-0.38

pertory

-0.37

POSITIVE LOGITS

MigrationBuilder

0.91

GEBURTSDATUM

0.78

/*

0.78

 XCTest

0.76

sizeCache

0.76

 الحره

0.75

DebuggerNonUser

0.71

richTextPanel

0.70

 AssemblyCompany

0.69

uxxxx

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.