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

MessageTagHelper

-0.85

Hauptartikel

-0.74

Diwedd

-0.69

 uska

-0.65

messageInfo

-0.64

őz

-0.63

 intptr

-0.63

AsUp

-0.63

 numberOfRows

-0.60

 fieldNum

-0.59

POSITIVE LOGITS

 zufolge

0.51

 fiscal

0.50

 outono

0.49

 kış

0.46

ArrowToggle

0.46

 year

0.45

ainte

0.43

~/

0.42

 aikana

0.42

 season

0.41

Activations Density 0.030%

No Comments

No Known Activations