INDEX

Explanations

words related to law, academics, and membership in organizations

oai_token-act-pair · gemini-2.0-flash

law and licensing

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

lasse

-0.47

makeText

-0.45

ripsi

-0.45

 camp

-0.43

Viitteet

-0.43

umsi

-0.42

BURGH

-0.42

 event

-0.41

سخ

-0.41

 emis

-0.40

POSITIVE LOGITS

GEBURTSDATUM

1.00

المناصب

0.87

<bos>

0.83

 виправивши

0.77

 ویکی‌پدی

0.77

 समीक्षक

0.71

 متعلقه

0.69

 itſelf

0.67

хьтан

0.67

fhir

0.65

Activations Density 2.318%

words related to law, academics, and membership in organizations

law and licensing

No Comments

No Known Activations