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

InjectAttribute

-0.80

AccessorTable

-0.79

 disambiguazione

-0.79

ArgsConstructor

-0.79

MLLoader

-0.74

 tartalo

-0.70

<unused52>

-0.68

 imagui

-0.68

<unused74>

-0.68

<unused51>

-0.68

POSITIVE LOGITS

 normalidad

0.43

 civilización

0.39

 desierto

0.36

 venganza

0.35

 vocación

0.33

 Formación

0.33

yet

0.33

 distância

0.32

 sorpresas

0.32

 laterales

0.31

Activations Density 0.000%

No Known Activations

This feature has no known activations.