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

CHA

-0.86

Statistics

-0.82

¥µ

-0.76

KI

-0.72

 SCHOOL

-0.68

 UNIVERS

-0.64

 Pryor

-0.63

Camp

-0.63

 sugg

-0.62

 WANT

-0.62

POSITIVE LOGITS

phabet

0.80

ogly

0.73

 Nigerian

0.72

bum

0.70

vance

0.70

 encryption

0.70

vantage

0.68

ouble

0.68

igmatic

0.67

fter

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.