INDEX

Explanations

nouns related to various institutions and their functions, including healthcare and legal contexts

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

followed by a period

np_acts-logits-general · gemini-2.0-flash

specific categories and entities

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

 StatelessWidget

-0.67

 StatefulWidget

-0.57

]))

-0.49

 preterm

-0.49

TEX

-0.48

 uplands

-0.47

 NUKAT

-0.47

 bosons

-0.46

 Boon

-0.46

 الرياضيه

-0.46

POSITIVE LOGITS

 hinweg

0.70

Personendaten

0.68

별

0.64

 pinulongan

0.63

stateProvider

0.62

 Мексичка

0.61

 StringTokenizer

0.61

 tertentu

0.56

mainAxisSize

0.55

Demografia

0.53

Activations Density 1.004%

nouns related to various institutions and their functions, including healthcare and legal contexts

followed by a period

specific categories and entities

No Comments

No Known Activations