INDEX

Explanations

structured data representations, especially in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 contextLoads

-0.55

omentos

-0.48

 photolibrary

-0.46

 userSchema

-0.46

 setTitle

-0.45

 magasiner

-0.45

 pajama

-0.44

ükemmel

-0.43

?</

-0.42

ೃ

-0.42

POSITIVE LOGITS

GEBURTSDATUM

0.88

webElementXpaths

0.87

:✨

0.83

oredCriteria

0.81

 <<<<<<<<<<<<<<

0.80

الحياه

0.76

jsxFileName

0.75

 autorytatywna

0.72

Personendaten

0.71

oa̍t

0.71

Activations Density 0.334%

structured data representations, especially in programming contexts

No Comments

No Known Activations