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

 captcha

-0.72

 praying

-0.67

 conferences

-0.66

 itch

-0.65

 rapport

-0.65

 positives

-0.61

Asset

-0.61

 storylines

-0.60

Cass

-0.60

 conference

-0.59

POSITIVE LOGITS

ľ

2.05

Ķ

1.20

ĺ

1.14

ķ

1.12

ļ

1.03

ĸ

1.01

ŀ

0.99

Ľ

0.99

¼

0.99

°

0.99

Activations Density 0.000%

No Known Activations

This feature has no known activations.