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

 jegy

-0.44

кви

-0.44

DUC

-0.36

format

-0.36

 format

-0.36

-0.35

 Folks

-0.34

 administr

-0.34

 formal

-0.34

ят

-0.34

POSITIVE LOGITS

bootstrapcdn

1.02

 esternos

0.96

 الرياضيه

0.95

 BoxDecoration

0.94

 Мексичка

0.93

Tikang

0.87

ConstraintMaker

0.86

 MediatR

0.85

SequentialGroup

0.82

djangoproject

0.82

Activations Density 0.092%

No Comments

No Known Activations