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

zech

-0.55

 Veld

-0.48

 Presence

-0.48

rady

-0.47

xase

-0.47

 presence

-0.46

 presente

-0.46

VideoCapture

-0.45

 Novo

-0.44

 presenti

-0.44

POSITIVE LOGITS

شهاد

0.98

ButtonModule

0.78

AccessorTable

0.75

<>());

0.74

PreExecute

0.72

<()>

0.69

الحياه

0.69

initComponents

0.67

 صوتيه

0.67

MatButtonModule

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.