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

 utafitiHapana

-1.02

leſs

-0.76

ArrowToggle

-0.73

NUMX

-0.70

lapsingToolbar

-0.65

ZA

-0.64

ividual

-0.64

ญิง

-0.63

 faſt

-0.63

felf

-0.63

POSITIVE LOGITS

 maybe

0.78

0.77

 really

0.75

 everybody

0.74

 yeah

0.74

you

0.72

 Everybody

0.71

 somebody

0.71

 Actually

0.69

Activations Density 0.031%

No Comments

No Known Activations