INDEX

Explanations

terms specific to medical conditions and treatments

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

Abbreviations followed by uppercase letters

np_acts-logits-general · gemini-2.0-flash

D-dimer, AAD, PE

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 تضيفلها

-0.56

 stessi

-0.53

colorbar

-0.52

 lapangan

-0.47

 numériques

-0.44

 temporaire

-0.43

 recent

-0.43

久保

-0.42

Véxase

-0.42

the

-0.42

POSITIVE LOGITS

ImageContext

0.68

roek

0.67

 Pelop

0.67

0.65

országban

0.65

ricanes

0.62

ruptedException

0.61

 Kurdistan

0.61

mybatisplus

0.60

AntiForgeryToken

0.60

Activations Density 1.522%

terms specific to medical conditions and treatments

Abbreviations followed by uppercase letters

D-dimer, AAD, PE

No Comments

No Known Activations