INDEX

Explanations

numerical data related to research studies

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

Numbers within or after journal citations

np_acts-logits-general · gemini-2.0-flash

bibliographic citations

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

 doch

-0.50

 оригіналу

-0.48

########.

-0.47

WaitGroup

-0.46

propTypes

-0.46

󠁮

-0.44

 ahor

-0.44

Solución

-0.43

IntoConstraints

-0.43

 nên

-0.42

POSITIVE LOGITS

PAGES

0.58

0.57

 publiée

0.57

0.56

 salutary

0.56

Efq

0.56

 woodcut

0.56

CloseOperation

0.55

Activations Density 0.115%

numerical data related to research studies

Numbers within or after journal citations

bibliographic citations

No Comments

No Known Activations