INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

MON

-0.78

yrics

-0.72

NYSE

-0.71

NetMessage

-0.71

QL

-0.68

 gust

-0.68

 ammon

-0.66

ROR

-0.65

DoS

-0.64

 vulner

-0.63

POSITIVE LOGITS

 Chapters

0.68

 Jobs

0.67

forth

0.66

 Isles

0.65

arta

0.65

alion

0.63

ãĥĺ

0.61

 Galile

0.61

naire

0.60

arte

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.