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

tonode

-0.45

 defStyle

-0.44

 Hubert

-0.44

もしろ

-0.44

AutoField

-0.41

 antis

-0.41

LookAnd

-0.41

 Résultat

-0.40

+#+

-0.40

 BoxFit

-0.39

POSITIVE LOGITS

 EconPapers

0.65

StackSize

0.49

 transfieras

0.45

 PopupWindow

0.44

ंदीखरीदारी

0.43

Mainly

0.42

 CanadaChoose

0.42

tagHelperRunner

0.41

NUMX

0.40

Kjelder

0.40

Activations Density 0.000%

No Known Activations

This feature has no known activations.