INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.UseText

-0.07

主治

-0.07

_OM

-0.06

IRTUAL

-0.06

istance

-0.06

 nelle

-0.06

.Entities

-0.06

ulner

-0.06

课外

-0.06

💶

-0.06

POSITIVE LOGITS

Designer

0.07

osopher

0.07

 evident

0.07

 theorists

0.07

运行

0.07

 reigning

0.07

시설

0.07

гля

0.06

批发市场

0.06

Activations Density 0.025%

No Known Activations