INDEX

Explanations

country names and their associations with various metrics or events

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

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

tvguidetime

-0.87

 disambiguazione

-0.70

 صوتيه

-0.68

ècle

-0.62

hoeddwyd

-0.59

ActionListener

-0.56

ensión

-0.56

 >=",

-0.56

dorp

-0.56

Искәрмәләр

-0.55

POSITIVE LOGITS

 giapponese

0.53

 Japan

0.52

 Giappone

0.49

 Scandinavia

0.49

messageInfo

0.48

Japan

0.48

 japan

0.48

 mukana

0.48

 Germany

0.48

 Japão

0.47

Activations Density 0.211%

country names and their associations with various metrics or events

No Comments

No Known Activations