INDEX

Explanations

technical programming terms and structures in snippets of code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

 ProtoMessage

-0.53

 الرياضيه

-0.51

 Normdatei

-0.50

 Chwiliwch

-0.48

الإنجليزية

-0.47

 voks

-0.46

 Bioaccumulative

-0.45

musica

-0.45

밌

-0.45

__(/*!

-0.44

POSITIVE LOGITS

ModelSerializer

0.39

complexContent

0.37

HandlerContext

0.37

WebVitals

0.36

expectedResult

0.35

ChildIndex

0.34

したもの

0.34

 JAXBElement

0.34

 disambiguazione

0.34

xsi

0.34

Activations Density 3.155%

technical programming terms and structures in snippets of code

No Comments

No Known Activations