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

ⓧ

-0.59

TPE

-0.56

messe

-0.55

simpleType

-0.54

GenerationType

-0.54

 Deutsch

-0.54

 Mehl

-0.54

 Pech

-0.54

-0.53

 ★★★

-0.53

POSITIVE LOGITS

IContainer

0.36

 suivants

0.35

一动

0.33

女兒

0.32

 Scaling

0.31

活跃

0.30

 reprodução

0.28

 respiración

0.28

 embaraz

0.28

Sw

0.28

Activations Density 0.000%

No Known Activations

This feature has no known activations.