INDEX

Explanations

numerical figures and statistical data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

__(/*!

-0.72

 useParams

-0.65

 useRouter

-0.64

serviceWorker

-0.60

'],

-0.59

withOpacity

-0.59

ycznego

-0.57

'])->

-0.56

ogno

-0.56

>):

-0.56

POSITIVE LOGITS

GEBURTSDATUM

0.74

 Référence

0.55

marvin

0.49

 limb

0.49

 povezave

0.48

 teş

0.44

Palmarès

0.44

Voci

0.43

DMETHOD

0.43

ChromeDriver

0.42

Activations Density 0.609%

numerical figures and statistical data

No Comments

No Known Activations