INDEX

Explanations

information related to technical processes and terms in scientific contexts

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

after capitalized words or abbreviations

np_acts-logits-general · gemini-2.0-flash

compound words or phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

WithIOException

-0.70

 autorytatywna

-0.66

Derbyniad

-0.65

 propOrder

-0.63

XmlEnum

-0.62

})();

-0.57

 >=",

-0.57

 LoggerFactory

-0.56

titleMargin

-0.53

XmlType

-0.53

POSITIVE LOGITS

Portail

0.63

WriteAttribute

0.63

interopRequire

0.61

ioutil

0.61

TypedDataSet

0.57

 समीक्षक

0.56

 BrowserModule

0.56

 CanadaChoose

0.55

териалы

0.54

Activations Density 6.620%

information related to technical processes and terms in scientific contexts

after capitalized words or abbreviations

compound words or phrases

No Comments

No Known Activations