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

SCP

-0.73

RIP

-0.72

okemon

-0.71

Station

-0.70

cca

-0.69

UTC

-0.68

--+

-0.66

Forest

-0.65

Ult

-0.64

XP

-0.63

POSITIVE LOGITS

neau

0.79

witz

0.75

 Adin

0.64

 largeDownload

0.63

iannopoulos

0.63

 darkened

0.62

illac

0.61

 mast

0.61

 freshman

0.61

 Brach

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.