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

 earthqu

-0.79

 challeng

-0.77

ilaterally

-0.76

 looph

-0.76

 mathemat

-0.75

 cryst

-0.74

 trave

-0.72

 advoc

-0.68

 nodd

-0.67

ruby

-0.67

POSITIVE LOGITS

amp

0.76

MW

0.70

ANE

0.69

OVER

0.66

Ap

0.66

AW

0.66

ew

0.66

ï¿½ï¿½

0.66

 Tradable

0.65

Copyright

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.