INDEX

Explanations

references to scientific publication details, such as ISSNs and citation formats

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

Tokens after a number and inside brackets

np_acts-logits-general · gemini-2.0-flash

ISSN and DOIs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/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.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 propOrder

-0.68

BufferException

-0.47

 ModelExpression

-0.46

complexType

-0.44

 Affaires

-0.39

fortawesome

-0.39

JspWriter

-0.39

MigrationBuilder

-0.39

 drewna

-0.39

 Administrativna

-0.38

POSITIVE LOGITS

 arşivlendi

0.57

Personensuche

0.57

 ISSN

0.54

ISSN

0.52

VIAF

0.52

存于互联网档案馆

0.51

 صوتيه

0.51

 disambiguazione

0.47

 nahilalakip

0.46

الحياه

0.46

Activations Density 0.383%

references to scientific publication details, such as ISSNs and citation formats

Tokens after a number and inside brackets

ISSN and DOIs

No Comments

No Known Activations