INDEX

Explanations

Amazon SageMaker lets you train

New Auto-Interp

Top Features by Cosine Similarity

Configuration

Prompts (Dashboard)

10,000 prompts, 128 tokens each

Dataset (Dashboard)

lmsys/lmsys-chat-1m

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

BMC

-0.09

biz

-0.09

ulo

-0.09

 Gross

-0.09

ADM

-0.08

 birthday

-0.08

Dro

-0.08

 Mant

-0.08

ULO

-0.08

angelog

-0.08

POSITIVE LOGITS

 Sage

0.21

 Amazon

0.18

 sage

0.16

.amazonaws

0.16

.amazon

0.16

Amazon

0.14

 amazon

0.13

mazon

0.13

 Kindle

0.13

amazon

0.13

Activations Density 0.018%