INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Archbishop

-0.67

 waiver

-0.66

 Interior

-0.63

 Cass

-0.63

 Pastebin

-0.62

 Shank

-0.62

caps

-0.62

 Emperor

-0.60

$$$$

-0.60

ingly

-0.59

POSITIVE LOGITS

ternity

0.81

 Â®

0.79

asio

0.78

arbon

0.74

lik

0.73

sembly

0.71

emis

0.69

hig

0.68

oola

0.68

ãĤ¸

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.