INDEX

Explanations

acknowledgments and gratitude expressions in research papers

oai_token-act-pair · gpt-4o-mini Triggered by @bot

expressing thanks and contributions

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 snippetHide

-0.60

GEBURTSDATUM

-0.49

 ویکی‌پدی

-0.45

 mijne

-0.45

MigrationBuilder

-0.44

 chofe

-0.44

 nonatomic

-0.44

 mierda

-0.42

 مشين

-0.42

 pagină

-0.41

POSITIVE LOGITS

最快更新

0.47

 contributing

0.44

 contributors

0.41

 Merci

0.40

 contributions

0.40

 merci

0.39

 الرياضيه

0.39

 invaluable

0.38

 institutional

0.37

 للاسماء

0.37

Activations Density 0.106%

acknowledgments and gratitude expressions in research papers

expressing thanks and contributions

No Comments

No Known Activations