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

NRS

-0.92

Tex

-0.73

Georgia

-0.73

Accept

-0.73

ilib

-0.70

ayette

-0.70

intern

-0.70

Adapt

-0.69

euro

-0.68

uds

-0.68

POSITIVE LOGITS

MpServer

0.75

terday

0.75

 Zoro

0.75

Kai

0.70

£ı

0.69

Zhu

0.68

 Unch

0.67

 quer

0.66

 Pagan

0.65

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.