INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_22

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 FormBuilder

-0.60

 définiti

-0.60

ETERS

-0.50

bietern

-0.50

ButtonModule

-0.49

 UserDao

-0.48

GIVEREF

-0.46

 prisonniers

-0.46

 pinulongan

-0.46

 cuadrados

-0.46

POSITIVE LOGITS

 projects

0.95

 assignments

0.74

 project

0.72

 Projects

0.71

projects

0.70

 situations

0.68

رشف

0.68

 betweenstory

0.67

Projects

0.67

 missions

0.65

Activations Density 0.113%

No Comments

No Known Activations