INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.24.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

ëłĲ

-0.25

ä»ĺè´¹

-0.25

åħļä¸Ńå¤®

-0.25

 growing

-0.24

 Georgia

-0.24

[method

-0.24

cmb

-0.23

 robust

-0.23

rer

-0.23

POSITIVE LOGITS

pering

0.30

çļĦæĸĩåĮĸ

0.27

igrant

0.27

èĢ³

0.27

uet

0.27

boolean

0.26

Ã©ri

0.25

å¤´èĦĳ

0.25

åĥ®

0.25

ä¼¦

0.24

Activations Density 0.381%

No Known Activations

This feature has no known activations.