INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

orem

-0.80

 Mysteries

-0.72

 Trem

-0.65

og

-0.65

rompt

-0.64

 hitch

-0.63

trak

-0.63

sburg

-0.62

phal

-0.62

sag

-0.61

POSITIVE LOGITS

Draft

0.74

 Lobby

0.68

ESE

0.66

ICE

0.65

Copy

0.64

.?

0.63

abuse

0.63

ãĤĬ

0.62

Liquid

0.61

UE

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.