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

ambique

-0.74

henge

-0.70

SequentialGroup

-0.69

 متعلقه

-0.69

ętr

-0.67

 الحره

-0.65

%)$

-0.64

minecraftforge

-0.63

artifactId

-0.63

#+#

-0.60

POSITIVE LOGITS

 Hong

1.19

Hong

0.96

 Hongkong

0.95

 Leung

0.92

 Taiwan

0.88

HK

0.83

 Taipei

0.78

 Macao

0.75

Taiwan

0.75

 Yuen

0.73

Activations Density 0.036%

No Comments

No Known Activations