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

 autorytatywna

-0.91

存于互联网档案馆

-0.91

 pinulongan

-0.82

rungsseite

-0.82

ConstraintMaker

-0.71

ExtendWith

-0.71

Odour

-0.69

 Geophysics

-0.68

AxisAlignment

-0.67

 تضيفلها

-0.67

POSITIVE LOGITS

 Medicare

0.96

 healthcare

0.83

 Medicaid

0.82

 coverage

0.82

Medicare

0.80

 health

0.73

 providers

0.72

 insurance

0.68

 provider

0.66

 Health

0.66

Activations Density 0.058%

No Comments

No Known Activations