INDEX

Explanations

references to research publications and collaborative studies

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

 tanı

-0.46

 Floor

-0.36

 provisoire

-0.35

Floor

-0.34

 disambiguazione

-0.33

GEBURTSDATUM

-0.33

Décès

-0.33

 floor

-0.32

ंदीखरीदारी

-0.32

 MERCHANT

-0.32

POSITIVE LOGITS

IsContent

0.63

 onAnimation

0.58

tableFuture

0.57

RenderAtEndOf

0.56

 onCreateView

0.56

WebVitals

0.55

 SqlCommand

0.54

sertation

0.54

mphony

0.52

fillText

0.51

Activations Density 1.389%

references to research publications and collaborative studies

No Comments

No Known Activations