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

 AssemblyCulture

-1.07

 Conley

-0.84

 Ariana

-0.84

setPreferredSize

-0.81

 Moreno

-0.77

+:+

-0.75

ึกษา

-0.75

SceneManagement

-0.73

########.

-0.73

Marlene

-0.71

POSITIVE LOGITS

zab

1.85

Zab

1.24

zab

1.20

Zab

1.10

TAKE

0.82

 took

0.73

taking

0.73

 заба

0.73

take

0.72

Dab

0.72

Activations Density 0.000%

No Known Activations

This feature has no known activations.