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

geist

-0.98

opian

-0.74

dragon

-0.71

meyer

-0.71

UCS

-0.69

 Sunny

-0.68

guy

-0.65

razen

-0.65

akeru

-0.65

 PHOTO

-0.64

POSITIVE LOGITS

":"/

0.83

raltar

0.71

Ħ¢

0.67

å¤§

0.65

orem

0.64

inion

0.64

fn

0.63

OUR

0.62

Ń·

0.62

ECTION

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.