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

fromnode

-0.76

RegressionTest

-0.73

 habet

-0.65

 ویکی‌پدی

-0.65

 '\\;'

-0.64

-0.63

 eorum

-0.63

'}),

-0.63

 surla

-0.62

AddHtmlAttribute

-0.59

POSITIVE LOGITS

my

0.89

 myself

0.86

 mijn

0.71

 моя

0.68

my

0.64

 meines

0.64

 mojej

0.64

 minha

0.63

 meiner

0.63

myself

0.61

Activations Density 0.163%

No Comments

No Known Activations