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

DragonMagazine

-0.84

eries

-0.75

irlf

-0.71

weeney

-0.71

itate

-0.70

Js

-0.70

incinn

-0.70

 glim

-0.69

VK

-0.68

aunders

-0.68

POSITIVE LOGITS

 contested

0.66

uria

0.64

 disputed

0.64

 Saddam

0.62

 Defensive

0.62

 Pillar

0.61

 defensive

0.61

 ballistic

0.60

 Alam

0.60

gran

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.