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

RenderAtEndOf

-0.75

AsUp

-0.74

 дописавши

-0.70

parsedMessage

-0.66

})));

-0.64

LookAnd

-0.63

)_/¯

-0.63

انيف

-0.63

afficheront

-0.61

GeneratedCode

-0.60

POSITIVE LOGITS

 ecológica

0.64

ftagPool

0.62

 alimentaria

0.58

 asiática

0.57

 Económica

0.54

 giustizia

0.54

endpush

0.49

jspx

0.49

 estratégica

0.49

 biochemistry

0.48

Activations Density 0.000%

No Known Activations

This feature has no known activations.