INDEX

Explanations

references to Australia, its citizens, and related contexts

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

Australia

np_acts-logits-general · gemini-2.0-flash

Australia and Australians

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

initialise

-0.61

Colour

-0.58

COLOUR

-0.56

 Programmes

-0.56

centred

-0.56

 centre

-0.55

fibre

-0.55

 specialise

-0.53

colour

-0.53

programme

-0.52

POSITIVE LOGITS

 Australian

1.56

 Australia

1.49

 Australians

1.42

 Aussie

1.38

Australia

1.36

Australian

1.36

 australian

1.33

 australiano

1.32

 Australien

1.26

 AUSTRALIA

1.25

Activations Density 0.104%

references to Australia, its citizens, and related contexts

Australia

Australia and Australians

No Comments

No Known Activations