INDEX

Explanations

references to individuals in leadership or influential roles

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

Canadian locations, organizations, and people

np_acts-logits-general · gemini-2.0-flash

Canada and Canadian

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

protoimpl

-0.71

tagHelperRunner

-0.69

favorite

-0.67

parsedMessage

-0.67

 Superan

-0.66

uș

-0.66

rawDesc

-0.65

 theater

-0.65

 otomatig

-0.65

theater

-0.65

POSITIVE LOGITS

 Canadian

1.31

 Canada

1.27

 Canadians

1.22

Canada

1.20

Canadian

1.19

 Ontario

1.17

カナダ

1.16

 Manitoba

1.16

 Toronto

1.14

 CANADIAN

1.13

Activations Density 0.243%

references to individuals in leadership or influential roles

Canadian locations, organizations, and people

Canada and Canadian

No Comments

No Known Activations