INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.png

-0.07

 Laboratories

-0.07

 activities

-0.07

_non

-0.06

 NORMAL

-0.06

plings

-0.06

_VARIABLE

-0.06

초

-0.06

PCs

-0.06

POSITIVE LOGITS

 Scalar

0.07

 trhu

0.06

.apps

0.06

irt

0.06

alan

0.06

rit

0.06

 små

0.06

 mains

0.05

alaxy

0.05

\a

0.05

Activations Density 0.031%

No Known Activations