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

 HIPAA

-0.74

tslib

-0.69

 Fitz

-0.69

eves

-0.69

 Picchu

-0.68

 médical

-0.67

 kneel

-0.66

rafat

-0.66

vartis

-0.65

kDa

-0.65

POSITIVE LOGITS

 consumers

1.66

 consumer

1.55

 Consumers

1.53

 Consumer

1.52

Consumer

1.39

Consumers

1.37

consumer

1.33

 CONSUMER

1.33

consumers

1.29

 Consum

1.20

Activations Density 0.012%

No Comments

No Known Activations