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

Interstitial

-0.77

abouts

-0.69

pton

-0.69

âĹ¼

-0.69

Ð´

-0.68

Finish

-0.67

soDeliveryDate

-0.64

earchers

-0.64

+++

-0.63

raviolet

-0.62

POSITIVE LOGITS

aniel

0.70

cp

0.70

istries

0.69

 Kore

0.69

Om

0.66

ciples

0.66

iour

0.66

cms

0.65

oped

0.65

ark

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.