INDEX

Explanations

mentions of significant figures and events in historical contexts

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

preceding question marks or exclamation marks

np_acts-logits-general · gemini-2.0-flash

racial stereotypes and historical oppression

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

 unknownFields

-0.79

<bos>

-0.78

ForValue

-0.72

EndProject

-0.71

 Мексичка

-0.70

QMetaType

-0.69

 ModelExpression

-0.68

yntaxException

-0.67

 незавершена

-0.66

Identyfik

-0.65

POSITIVE LOGITS

 рекомендую

0.60

(=

0.57

 bluish

0.56

toLocale

0.55

っこう

0.54

 Moslem

0.50

 nikdy

0.50

 healthful

0.49

nmgp

0.48

 kawaii

0.48

Activations Density 0.511%

mentions of significant figures and events in historical contexts

preceding question marks or exclamation marks

racial stereotypes and historical oppression

No Comments

No Known Activations