INDEX

Explanations

math formulas or the phrase "I don't"

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Hzfinfdu/SlimPajama-3B and open-r1/OpenR1-Math-220k

Features

32,768

Data Type

float32

Hook Name

blocks.17.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pace

-0.06

Lug

-0.06

 prim

-0.06

itionally

-0.06

 space

-0.06

POSITIVE LOGITS

achel

0.07

åĵª

0.06

ossier

0.06

ieg

0.06

ekim

0.06

ÙĬØ§Ø±

0.06

.dds

0.06

AffineTransform

0.06

lemn

0.06

URLException

0.06

Activations Density 0.033%