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

DragonMagazine

-0.89

senal

-0.86

regor

-0.75

abase

-0.71

eatures

-0.71

-0.70

Interstitial

-0.68

gio

-0.67

atures

-0.67

idable

-0.67

POSITIVE LOGITS

upon

0.69

ciples

0.65

ject

0.64

ruciating

0.62

GOT

0.58

 Medicaid

0.56

âĶĢâĶĢ

0.56

OH

0.55

ISE

0.55

IU

0.55

Activations Density 0.000%

No Known Activations

This feature has no known activations.