INDEX

Explanations

terms and phrases related to biological and medical processes

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

after specific symbols/numbers

np_acts-logits-general · gemini-2.0-flash

error codes and identifiers

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

Tembelea

-0.60

 resourceCulture

-0.55

تقاوى

-0.53

GEBURTSDATUM

-0.52

 tartalomajánló

-0.50

hoeddwyd

-0.50

@"/

-0.50

Glej

-0.49

 nonUne

-0.48

 ویکی‌پدی

-0.48

POSITIVE LOGITS

 Paglinawan

0.46

 surla

0.44

hynch

0.44

uinal

0.43

 errorCode

0.43

ConstraintMaker

0.42

comuna

0.41

 productName

0.40

unhofer

0.40

 productId

0.39

Activations Density 1.251%

terms and phrases related to biological and medical processes

after specific symbols/numbers

error codes and identifiers

No Comments

No Known Activations