INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

itans

-0.88

riots

-0.85

 athlet

-0.74

anium

-0.70

agara

-0.68

 lashes

-0.68

igers

-0.68

 reluct

-0.67

ascript

-0.64

 abdom

-0.63

POSITIVE LOGITS

 Logged

0.84

stem

0.73

hart

0.71

 Karin

0.69

yz

0.67

ward

0.64

BIL

0.62

 Modified

0.62

lier

0.61

HUD

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.