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.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

nym

-0.27

âİ¦

-0.26

manship

-0.26

æį¨

-0.24

æł¼å°Ķ

-0.24

á´ı

-0.24

æ¹ĸ

-0.24

Outlined

-0.24

ROAD

-0.24

pac

-0.24

POSITIVE LOGITS

 kits

0.28

IW

0.27

åĲĿ

0.25

éĹ¯

0.25

 survives

0.24

ç½Ħ

0.24

çĳĹ

0.24

peg

0.23

ensor

0.23

Activations Density 1.067%

No Known Activations

This feature has no known activations.