INDEX

Explanations

terms related to political and social issues involving control and regulations

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

after articles or prepositions

np_acts-logits-general · gemini-2.0-flash

projection display

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

}}]{

-0.74

 kasarigan

-0.71

 myſelf

-0.70

 Anſ

-0.67

KindOfClass

-0.66

 pleaſure

-0.65

$_"

-0.65

adeloupe

-0.65

Kjelder

-0.64

standers

-0.63

POSITIVE LOGITS

 يتيمه

0.66

AnchorStyles

0.60

GeoNames

0.59

Gemeinsame

0.58

BeginInit

0.57

LookAnd

0.54

IsContent

0.54

PreferredItem

0.54

 VizieR

0.53

featureID

0.52

Activations Density 2.379%

terms related to political and social issues involving control and regulations

after articles or prepositions

projection display

No Comments

No Known Activations