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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ATA

-0.84

 guiName

-0.81

manship

-0.77

ofi

-0.70

usha

-0.68

essor

-0.67

iaz

-0.65

ership

-0.64

inately

-0.62

 Baird

-0.61

POSITIVE LOGITS

 Reboot

0.69

00200000

0.69

 Oops

0.66

 Alic

0.65

Pause

0.65

Reviewed

0.64

 Turns

0.64

acements

0.63

TextColor

0.63

 declarations

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.