INDEX

Explanations

terms related to emotions and their classification in a programming or machine learning context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100

Prompts (Dashboard)

24,576 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

AnchorStyles

-0.42

Formik

-0.40

ChildScrollView

-0.39

VersionUID

-0.38

ptid

-0.36

 Pante

-0.36

 work

-0.34

WithMany

-0.33

ChatColor

-0.33

StructEnd

-0.32

POSITIVE LOGITS

WebVitals

0.56

 Autorizaciones

0.52

 Geſ

0.52

gdala

0.50

 torchvision

0.49

исленность

0.49

MediaStore

0.48

 dieſen

0.47

 BoxFit

0.45

 Geſch

0.44

Activations Density 0.359%

terms related to emotions and their classification in a programming or machine learning context

No Comments

No Known Activations