INDEX

Explanations

mentions of Australia and associated terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

="#

-0.77

Delaware

-0.68

 nastro

-0.68

LEncoder

-0.67

+"

-0.66

.’

-0.66

 Spill

-0.65

={"

-0.64

</b>

-0.64

()+"

-0.63

POSITIVE LOGITS

 Australia

1.74

 Australian

1.54

Australia

1.51

 Australians

1.47

 AUSTRALIA

1.41

australia

1.38

 australia

1.34

 australian

1.32

ALIAN

1.29

 Aussie

1.28

Activations Density 0.042%

mentions of Australia and associated terms

No Comments

No Known Activations