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

ArrowToggle

-0.76

 MessageBoxIcon

-0.69

IndentedString

-0.67

LookAnd

-0.66

PreferredItem

-0.64

aarrggbb

-0.63

djangoproject

-0.62

SharedDtor

-0.62

 StringTokenizer

-0.62

 jspb

-0.62

POSITIVE LOGITS

 AssemblyTitle

0.66

batis

0.59

 précédents

0.57

openConnection

0.55

knex

0.55

Discografia

0.54

 ordinaires

0.54

 setempat

0.52

 relatifs

0.52

 sayap

0.51

Activations Density 0.008%

No Comments

No Known Activations