INDEX

Explanations

references to special features and extras associated with a collection of episodes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

SpringBoot

-0.54

Clients

-0.46

 cantando

-0.46

ViewImports

-0.45

 chrétien

-0.45

ImageIO

-0.45

 Clients

-0.44

 denuncia

-0.44

 elettrico

-0.44

 aliran

-0.44

POSITIVE LOGITS

出版年

0.80

MLLoader

0.71

 esterni

0.64

 الحره

0.64

ValueStyle

0.61

issenschaft

0.58

 Paglinawan

0.57

存于互联网档案馆

0.57

addGap

0.56

addCriterion

0.56

Activations Density 0.380%

references to special features and extras associated with a collection of episodes

No Comments

No Known Activations