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

bour

-0.75

dimension

-0.75

rendered

-0.72

street

-0.66

facing

-0.66

uracy

-0.66

lease

-0.63

 Address

-0.63

xton

-0.63

machine

-0.63

POSITIVE LOGITS

 STAR

0.72

uten

0.70

 spoiler

0.66

éĹĺ

0.66

UGH

0.66

 odds

0.66

SUN

0.65

 TRUMP

0.64

 Survivors

0.64

inav

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.