INDEX

Explanations

references to Canadian provinces and territories

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

Canadian provinces and citizens

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

uș

-0.54

ViewFeatures

-0.53

Hochspringen

-0.51

 Etats

-0.47

Manbalar

-0.46

maß

-0.45

protoimpl

-0.45

 creș

-0.43

liferay

-0.43

 Еще

-0.42

POSITIVE LOGITS

 Canada

1.12

 Canadian

1.11

Canada

1.06

 Canadians

1.03

カナダ

1.02

Canadian

1.01

加拿大

1.01

 CANADA

0.99

TAWA

0.98

 Toronto

0.96

Activations Density 0.197%

references to Canadian provinces and territories

Canadian provinces and citizens

No Comments

No Known Activations