INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 resourceCulture

-0.78

 дописавши

-0.78

 ProtoMessage

-0.74

Референце

-0.69

 useAppContext

-0.69

 autorytatywna

-0.68

sizeCache

-0.67

makedirs

-0.65

MessageTagHelper

-0.63

KommentareTeilen

-0.61

POSITIVE LOGITS

enschappelijke

0.84

getOut

0.82

shadowRadius

0.72

Collegamenti

0.64

Ouv

0.63

FXMLLoader

0.59

useNewUrlParser

0.50

Xna

0.49

Ouv

0.49

inSlope

0.45

Activations Density 0.000%

No Known Activations

This feature has no known activations.