INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.24.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Italijanski

-0.72

 Мексичка

-0.65

 Италијани

-0.59

تقاوى

-0.57

 Савезне

-0.57

 المعيارى

-0.57

Personendaten

-0.56

webElementXpaths

-0.56

Jeografia

-0.56

MigrationBuilder

-0.55

POSITIVE LOGITS

’

0.39

 defaultstate

0.38

 مشين

0.36

isor

0.36

mathrm

0.35

}}}{\

0.35

 miserable

0.34

pres

0.34

\}\

0.33

Activations Density 0.000%

No Known Activations

This feature has no known activations.