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

bilt

-0.79

WORK

-0.74

itia

-0.73

zman

-0.71

former

-0.71

hari

-0.71

perfect

-0.71

PRESS

-0.70

ickets

-0.69

akeru

-0.68

POSITIVE LOGITS

 anonymity

0.73

 sided

0.64

estic

0.63

axe

0.63

 amnesty

0.61

ief

0.61

oused

0.60

 watering

0.58

 eyed

0.58

iliary

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.