INDEX

Explanations

phrases indicating frequency or occurrence

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

Follows the word "Every"

np_acts-logits-general · gemini-2.0-flash

every instance

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 arşivlendi

-0.68

or

-0.56

//

-0.55

MockBean

-0.55

Or

-0.54

erráneo

-0.54

Bauer

-0.52

DaoImpl

-0.49

pate

-0.48

Zacks

-0.48

POSITIVE LOGITS

every

1.34

 every

1.32

 Every

1.31

 EVERY

1.27

Every

1.27

EVERY

1.26

 Anſ

0.97

 Monfieur

0.96

 Ogni

0.96

 Majefty

0.93

Activations Density 0.097%

phrases indicating frequency or occurrence

Follows the word "Every"

every instance

No Comments

No Known Activations