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

abestanden

-0.60

 виправивши

-0.56

]='\

-0.54

ativement

-0.52

eraard

-0.50

ⓘ

-0.50

oredCriteria

-0.49

mô

-0.47

tais

-0.47

adaptiveStyles

-0.47

POSITIVE LOGITS

LabelTagHelper

1.70

InputBorder

0.76

IntoConstraints

0.63

 MatDialog

0.63

yafet

0.57

 vettor

0.56

 fijo

0.56

 InputDecoration

0.56

 promocional

0.54

RequestMapping

0.54

Activations Density 0.000%

No Known Activations

This feature has no known activations.