INDEX

Explanations

references to scientific journals and articles

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

請繼續往下閱讀

-0.60

 Numerade

-0.60

KommentareTeilen

-0.57

 myſelf

-0.55

፩

-0.54

 ويكيپيديا

-0.53

 themſelves

-0.51

 informée

-0.50

 houſe

-0.50

arrings

-0.50

POSITIVE LOGITS

genza

0.35

 maîtrise

0.33

 memen

0.33

 riserv

0.32

Naming

0.32

 significados

0.30

-|-

0.30

 médicale

0.30

lukan

0.29

 spiller

0.29

Activations Density 0.428%

references to scientific journals and articles

No Comments

No Known Activations