INDEX

Explanations

scientific terminology related to study results and causes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

RetentionPolicy

-0.48

 تضيفلها

-0.48

 Baillargeon

-0.46

 alligator

-0.43

 dragonfly

-0.42

 exposition

-0.42

 courtier

-0.39

πον

-0.39

 platform

-0.39

 Montagne

-0.39

POSITIVE LOGITS

ngdoc

0.80

 jspb

0.75

AndEndTag

0.71

IUrlHelper

0.70

Diweddarwch

0.70

 Administrativna

0.69

SuppressMessage

0.68

'}),

0.66

ApJ

0.66

 Мексичка

0.66

Activations Density 1.304%

scientific terminology related to study results and causes

No Comments

No Known Activations