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

Choice

-0.71

Chair

-0.68

ogens

-0.67

 Vest

-0.64

 univers

-0.64

Nusra

-0.63

 Printing

-0.62

 Checking

-0.61

Arg

-0.61

onom

-0.61

POSITIVE LOGITS

antz

0.82

 incompet

0.78

renheit

0.66

tg

0.65

aries

0.65

 thirsty

0.64

ateur

0.62

irie

0.61

 badly

0.60

ushima

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.