INDEX

Explanations

technical terms and references related to programming and web technologies

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 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

 travaillons

-0.59

ordinaire

-0.54

 betweenstory

-0.53

олові

-0.52

<tfoot>

-0.52

UnsafeEnabled

-0.51

InstrumentedTest

-0.51

 optimal

-0.51

 emerged

-0.51

 Organization

-0.50

POSITIVE LOGITS

 onOptions

0.57

bitField

0.49

+:+

0.49

enumi

0.48

uco

0.48

bootstrapcdn

0.47

addGroup

0.47

Hiring

0.47

forChild

0.46

Ộ

0.45

Activations Density 0.406%

technical terms and references related to programming and web technologies

No Comments

No Known Activations