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

elsen

-0.78

bleacher

-0.76

odi

-0.73

psc

-0.73

\'

-0.72

vernment

-0.70

oji

-0.69

ilitarian

-0.69

edia

-0.68

OSH

-0.68

POSITIVE LOGITS

inctions

0.71

 empires

0.70

 Conquest

0.69

 Sahara

0.69

ados

0.67

assic

0.64

imar

0.64

 probable

0.63

 Vega

0.62

 quer

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.