references to financial metrics and performance indicators

New Auto-Interp

Top Features by Cosine Similarity

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.18

 thousand

-0.17

-0.16

è¸

-0.16

Û°Û°

-0.15

-0.14

_reserve

-0.14

POSITIVE LOGITS

0.22

0.21

Activations Density 0.341%