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

#+#

-0.57

toLowerCase

-0.55

elux

-0.50

unched

-0.50

vosti

-0.49

volles

-0.48

UNCH

-0.47

inctive

-0.47

capit

-0.46

◾

-0.46

POSITIVE LOGITS

 distance

1.20

 distant

1.19

 distances

1.13

 distanced

1.07

distant

1.07

 distante

1.05

 élo

1.04

 Distant

1.02

 Distance

1.02

 DISTANCE

1.01

Activations Density 0.103%

No Comments

No Known Activations