INDEX

Explanations

references to specific fashion brands or designers

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.33.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

❉

-0.49

ंदीखरीदारी

-0.48

الإنجليزية

-0.48

Tasty

-0.46

Ezek

-0.46

 Ezekiel

-0.46

 AWESOME

-0.45

 awesome

-0.44

Etsy

-0.44

 gamis

-0.44

POSITIVE LOGITS

AndEndTag

0.44

 فريبيس

0.41

SharedDtor

0.40

 ObjectParameter

0.36

 pinulongan

0.36

ConstraintMaker

0.36

 pregunto

0.36

MessageOf

0.35

 écoulé

0.35

xrTableCell

0.35

Activations Density 0.102%

references to specific fashion brands or designers

No Known Activations