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

 contrace

-0.83

soever

-0.74

 princ

-0.74

 predec

-0.74

 undermin

-0.73

 quar

-0.69

 compan

-0.69

 streng

-0.69

 tram

-0.69

 philos

-0.68

POSITIVE LOGITS

zanne

0.88

anny

0.75

ainer

0.74

assembly

0.70

inator

0.70

IDER

0.69

tty

0.68

ickson

0.68

idation

0.68

aque

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.