INDEX

Explanations

punctuation marks and quotes

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

Quotation marks followed by attribution

np_acts-logits-general · gemini-2.0-flash

attribution after quotes

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RenderAtEndOf

-0.54

empl

-0.51

点此举报

-0.51

 своя

-0.50

qrstuvwxyz

-0.49

 autorytatywna

-0.48

 Biôgrafia

-0.48

 joaat

-0.48



-0.47

 chi̍t

-0.47

POSITIVE LOGITS

 said

0.52

帖最后由

0.46

,’’

0.43

,''

0.42

 says

0.42

,"

0.42

),"

0.41

he

0.40

 exclaimed

0.39

 تضيفلها

0.39

Activations Density 0.097%

punctuation marks and quotes

Quotation marks followed by attribution

attribution after quotes

No Comments

No Known Activations