INDEX

Explanations

JavaScript or Python syntax related to object properties and methods

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

ch

-0.52

Ch

-0.49

Fe

-0.49

an

-0.49

pri

-0.48

Caso

-0.48

cho

-0.48

getti

-0.47

Ke

-0.46

ko

-0.46

POSITIVE LOGITS

=$?

0.99

webElementXpaths

0.94

 AssemblyProduct

0.89

TintMode

0.89

TagMode

0.89

 propOrder

0.88

 otomatig

0.86

Personensuche

0.86

 linkovi

0.83

 oprot

0.80

Activations Density 0.247%

JavaScript or Python syntax related to object properties and methods

No Comments

No Known Activations