INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ronic

-0.81

ertodd

-0.79

hawk

-0.75

vier

-0.68

rals

-0.67

ynt

-0.66

eworthy

-0.65

icket

-0.65

jen

-0.65

 headlights

-0.64

POSITIVE LOGITS

 Duchess

0.76

 Brav

0.72

åĲ

0.69

ä¸Ń

0.66

 Rober

0.65

 Falk

0.65

 TAMADRA

0.65

 Brun

0.64

 Abuse

0.63

 Shinzo

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.