INDEX

Explanations

references to Ukraine and related geopolitical terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 تانيه

-0.56

bukkit

-0.56

memoized

-0.55

 Administrativna

-0.52

 CreateTagHelper

-0.52

 slap

-0.52

Демографія

-0.50

 linkovi

-0.48

 cherchés

-0.48

Clo

-0.47

POSITIVE LOGITS

 Ukrainian

1.66

 Ukraine

1.65

Ukraine

1.50

Ukrainian

1.50

 Ukrainians

1.45

 ukraine

1.39

 Kyiv

1.34

ukraine

1.31

 ukrain

1.30

 Ukraina

1.22

Activations Density 0.245%

references to Ukraine and related geopolitical terms

No Comments

No Known Activations