INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 Olsson

-0.36

 Erickson

-0.36

 Mühle

-0.36

 Atenas

-0.35

jamientos

-0.35

 Andersson

-0.35

 Lindberg

-0.34

 Steuer

-0.33

 Rauch

-0.33

 Persson

-0.32

POSITIVE LOGITS

 BoxFit

7.38

 MainAxisSize

1.19

 TextAlign

1.09

 FetchType

1.02

 AssemblyVersion

0.99

 BorderRadius

0.97

ChildScrollView

0.97

 TextInputType

0.96

 BoxDecoration

0.94

AxisAlignment

0.93

Activations Density 0.000%

No Known Activations

This feature has no known activations.