INDEX

Explanations

mathematical expressions and their properties, particularly focusing on positivity and negativity of values

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

open-r1/OpenR1-Math-220k

Features

32,768

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.07

IME

-0.07

-0.06

alar

-0.06

roe

-0.06

POSITIVE LOGITS

oup

0.08

ovÃŃ

0.06

Ð½Ð¸Ð½Ð°

0.06

á»ĵn

0.06

prÃ¡v

0.06

wh

0.06

_cmos

0.06

tring

0.05

aya

0.05

ikan

0.05

Activations Density 0.063%