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

ivable

-0.79

 VIDEOS

-0.69

ÃĥÃĤ

-0.69

®

-0.68

 respons

-0.63

soDeliveryDate

-0.62

gomery

-0.62

UX

-0.62

Þ

-0.62

iasis

-0.61

POSITIVE LOGITS

olith

0.73

growth

0.72

 goose

0.71

 scapego

0.70

spr

0.68

ads

0.63

ppings

0.62

otrop

0.61

improve

0.61

opsy

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.