INDEX

Explanations

terms related to international politics and conflict

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

 trajets

-0.54

 Bombay

-0.49

سطس

-0.49

Alf

-0.48

 lobster

-0.48

 stockings

-0.47

 Adirond

-0.46

èges

-0.46

 تانيه

-0.45

Jakarta

-0.45

POSITIVE LOGITS

 Ukrainian

1.59

 Ukraine

1.55

 Ukrainians

1.44

Ukraine

1.41

Ukrainian

1.34

 Kyiv

1.33

 ukrain

1.31

Ukra

1.23

 Ukra

1.17

 Ukrain

1.16

Activations Density 0.111%

terms related to international politics and conflict

No Comments

No Known Activations