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

AccessorTable

-0.95

 AssemblyCulture

-0.94

awtextra

-0.92

 EconPapers

-0.83

AddTagHelper

-0.79

ValueStyle

-0.79

NOPQRST

-0.78

 StatelessWidget

-0.76

]")]

-0.74

__':

-0.73

POSITIVE LOGITS

Clik

0.45

 bocas

0.43

ondy

0.43

@@

0.43

Famille

0.43

 https

0.42

anim

0.42

nå

0.42

{'

0.41

Activations Density 0.082%

No Comments

No Known Activations