INDEX

Explanations

medical terminology and statistical analysis related to health studies

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

Preceding words of non-English text

np_acts-logits-general · gemini-2.0-flash

measurements and enzymes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 vlasy

-0.62

 vzduchu

-0.59

 vodou

-0.58

 kereszt

-0.57

 łóż

-0.57

ýš

-0.55

ższych

-0.55

 przód

-0.54

 gwaran

-0.54

 úrov

-0.54

POSITIVE LOGITS

 ujednoznacz

0.89

Witam

0.75

 استنادى

0.74

 nakalista

0.73

DeleteBehavior

0.72

ViewImports

0.68

styleType

0.67

 Lewandowski

0.65

RectangleBorder

0.64

Przypisy

0.63

Activations Density 0.087%

medical terminology and statistical analysis related to health studies

Preceding words of non-English text

measurements and enzymes

No Comments

No Known Activations