INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

1,048,576

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 kvinder

-0.66

 varandra

-0.65

 samfun

-0.63

bootstrapcdn

-0.62

 artificiales

-0.60

 espagnole

-0.59

 contemporaine

-0.58

 rodea

-0.55

ValueStyle

-0.55

 Espagne

-0.55

POSITIVE LOGITS

]")]

0.97

0.60

بوابة

0.60

)}</

0.59

BeginContext

0.54

########.

0.54

 <<<<<<<<<<<<<<

0.53

ieras

0.52

 jLabel

0.52

Referències

0.52

Activations Density 0.000%

No Known Activations

This feature has no known activations.