INDEX

Explanations

proper nouns, specifically names

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

Followed by Korean surnames

np_acts-logits-general · gemini-2.0-flash

Korean surnames

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 autorytatywna

-0.59

 Chinese

-0.50

 Beijing

-0.49

 Weibo

-0.49

Beijing

-0.49

saraba

-0.49

complexContent

-0.49

 vendeurs

-0.46

الدراسه

-0.46

zugehen

-0.46

POSITIVE LOGITS

 Park

1.18

Park

1.03

 PARK

0.97

 park

0.95

park

0.92

PARK

0.84

 پارک

0.71

 Shim

0.71

 Baik

0.70

Kim

0.69

Activations Density 0.132%

proper nouns, specifically names

Followed by Korean surnames

Korean surnames

No Comments

No Known Activations