INDEX

Explanations

keywords and terms related to historical or political contexts in Japan

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

Japan or Japanese

np_acts-logits-general · gemini-2.0-flash

Japan and Japanese language

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

derry

-0.66

 Belize

-0.56

 facie

-0.53

 bezeichneter

-0.48

-0.47

Belize

-0.47

withOpacity

-0.47

 متعلقه

-0.45

 Barbuda

-0.45

enerys

-0.43

POSITIVE LOGITS

 Japanese

1.86

 Japan

1.85

Japan

1.66

Japanese

1.58

 JAPAN

1.52

 Japón

1.51

 japan

1.51

 Jepang

1.45

 Tokyo

1.45

 japanese

1.44

Activations Density 1.203%

keywords and terms related to historical or political contexts in Japan

Japan or Japanese

Japan and Japanese language

No Comments

No Known Activations