INDEX

Explanations

phrases related to sending messages or emails

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

emails, messages, or contact information

np_acts-logits-general · gemini-2.0-flash

communication and messages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

DockStyle

-0.87

 Мексичка

-0.85

SourceChecksum

-0.81

 للاسماء

-0.79

 Administrativna

-0.79

 مشين

-0.75

 Biôgrafia

-0.73

 ویکی‌پدی

-0.72

aarrggbb

-0.72

 utafitiHapana

-0.70

POSITIVE LOGITS

 email

1.81

 emails

1.58

 message

1.50

 messages

1.50

 Email

1.39

email

1.37

Email

1.33

 mail

1.26

 EMAIL

1.25

 Emails

1.21

Activations Density 0.231%

phrases related to sending messages or emails

emails, messages, or contact information

communication and messages

No Comments

No Known Activations