INDEX

Explanations

the preposition "de" in various contexts

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

"de" followed by a word

np_acts-logits-general · gemini-2.0-flash

de recherche

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

TestingModule

-0.69

WillAppear

-0.67

NameInMap

-0.66

TabIndex

-0.65

 itſelf

-0.63

 AssemblyCulture

-0.63

 Italie

-0.62

UnitTesting

-0.62

 hamilton

-0.59

 AssemblyTitle

-0.59

POSITIVE LOGITS

 BaseActivity

0.53

la

0.51

出版年

0.49

uscular

0.49

chakra

0.48

 flesta

0.48

cherichia

0.47

bergement

0.47

ingdon

0.47

ванные

0.47

Activations Density 0.034%

the preposition "de" in various contexts

"de" followed by a word

de recherche

No Comments

No Known Activations