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

natureconservancy

-0.80

Aub

-0.77

 Siri

-0.74

 ðŁĳ

-0.73

 Koen

-0.73

Tip

-0.72

Cour

-0.69

 Summers

-0.69

DN

-0.69

Tips

-0.69

POSITIVE LOGITS

 athlet

0.80

ucha

0.76

iatric

0.76

AMI

0.75

olitan

0.73

]-

0.73

 Wrestling

0.68

uda

0.68

umper

0.67

 wrestler

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.