INDEX

Explanations

articles such as "a" and the word "are".

oai_token-act-pair · gemini-2.0-flash

a

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-0.91

ArrowToggle

-0.68

Portail

-0.57

(@"%@",

-0.57

ViewImports

-0.53

RegistryLite

-0.53

مراجع

-0.51

BeforeClass

-0.51

 ligiloj

-0.51

☆☆

-0.50

POSITIVE LOGITS

出版年

0.64

 fraî

0.62

الصفحه

0.62

்த

0.61

Revenir

0.60

AnchorStyles

0.59

CppMethod

0.58

CloseOperation

0.57

ándolo

0.56

rited

0.56

Activations Density 1.612%

articles such as "a" and the word "are".

a

No Comments

No Known Activations