INDEX

Explanations

parenthetical asides and words that appear in opinion articles

oai_token-act-pair · gemini-2.0-flash

political/news commentary

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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>

-0.60

RestController

-0.56

 ElementRef

-0.54

cheiben

-0.49

cheibe

-0.49

BeginInit

-0.48

NUMX

-0.48

INER

-0.48

中略

-0.48

setAdapter

-0.47

POSITIVE LOGITS

:✨

0.76

GEBURTSDATUM

0.74

RemoveField

0.73

PreferredItem

0.63

AlterField

0.61

تقاوى

0.56

horabuena

0.54

الحياه

0.53

 Normdatei

0.52

 fédé

0.52

Activations Density 3.590%

parenthetical asides and words that appear in opinion articles

political/news commentary

No Comments

No Known Activations