INDEX

Explanations

questions or inquiries related to programming or coding contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 שוליים

-0.62

reciated

-0.55

 BeautifulSoup

-0.55

Iné

-0.53

namese

-0.52

anganronpa

-0.51

itename

-0.51

romycin

-0.50

 enrol

-0.49

SceneManagement

-0.48

POSITIVE LOGITS

出版年

0.63

czaj

0.58

 fapt

0.55

parency

0.54

Demografía

0.53

 bandeira

0.51

cinnati

0.49

 obicei

0.48

WriteBarrier

0.48

XmlAccessorType

0.48

Activations Density 0.173%

questions or inquiries related to programming or coding contexts

No Comments

No Known Activations