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

いた

-0.81

ocytosis

-0.74

tyard

-0.74

zation

-0.71

 Guzmán

-0.70

<eos>

-0.69

izations

-0.69

__.

-0.68

POSITIVE LOGITS

ORE

1.42

 Tare

1.35

Ure

1.34

DRE

1.31

 Kure

1.25

 Sare

1.24

 Hore

1.23

 Vire

1.20

 Nare

1.17

Ore

1.16

Activations Density 0.093%

No Comments

No Known Activations