INDEX

Explanations

proper nouns and specific references to people, titles, and organizations

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

with diacritics/accents

np_acts-logits-general · gemini-2.0-flash

accented words or proper nouns

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 المعيارى

-0.83

وردار

-0.61

 cherchés

-0.60

 Paglinawan

-0.59

mogat

-0.59

Љ

-0.58

csolódó

-0.57

 estimés

-0.56

 access

-0.56

 похо

-0.55

POSITIVE LOGITS

 doughnuts

0.85

acán

0.78

})`

0.75

 Beyoncé

0.75

hitheatre

0.75

 Yucatán

0.74

 Citroën

0.74

 Bogotá

0.74

 Erdoğan

0.73

Portail

0.73

Activations Density 0.301%

proper nouns and specific references to people, titles, and organizations

with diacritics/accents

accented words or proper nouns

No Comments

No Known Activations