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

webElementXpaths

-0.72

SourceChecksum

-0.71

NameInMap

-0.66

PropertyChanging

-0.65

adaptiveStyles

-0.65

 dynamic

-0.59

makeConstraints

-0.57

Personendaten

-0.57

ServletException

-0.57

ьаж

-0.56

POSITIVE LOGITS

</i>

0.87

endphp

0.79

</b>

0.69

'{}

0.64

Programm

0.61

 الحره

0.58

ellery

0.58

URLException

0.57

ophon

0.57

</em>

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.