INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.23.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 labelled

-0.08

 labeled

-0.07

_relative

-0.07

 hauling

-0.06

ruise

-0.06

 Intro

-0.06

 Tổng

-0.06

 मई

-0.06

 Liberty

-0.06

POSITIVE LOGITS

(土

0.06

 волос

0.06

__()↵

0.06

 demands

0.06

 Conservatives

0.06

้านด

0.06

時間

0.06

еления

0.06

BorderColor

0.06

USB

0.06

Activations Density 0.047%

No Known Activations