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

 défaite

-0.46

壤

-0.45

 Públicas

-0.42

 verliert

-0.39

Оста

-0.39

 już

-0.39

 obicei

-0.38

 يتيمه

-0.38

 müh

-0.38

Wię

-0.38

POSITIVE LOGITS

GEBURTSDATUM

0.82

synthesize

0.82

ngdoc

0.80

:✨

0.76

Hentet

0.73

InlineData

0.72

+#+

0.71

LEncoder

0.70

Portale

0.70

 AssemblyTitle

0.69

Activations Density 0.024%

No Comments

No Known Activations