INDEX

Explanations

non-English text, programming code, and chatty informal language used in online forums

oai_token-act-pair · gemini-2.0-flash

Foreign languages

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 EconPapers

-0.78

 تضيفلها

-0.75

 يتيمه

-0.73

 дописавши

-0.71

 disambiguazione

-0.69

IntoConstraints

-0.67

Hozzáférés

-0.67

featureID

-0.66

verwijspagina

-0.63

rungsseite

-0.60

POSITIVE LOGITS

 بودم

0.59

 هستم

0.55

ceğim

0.55

'/',

0.54

])[

0.54

 lenne

0.54

 ندارم

0.54

 چیه

0.53

خخ

0.52

WinForms

0.51

Activations Density 0.731%

non-English text, programming code, and chatty informal language used in online forums

Foreign languages

No Comments

No Known Activations