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

Reviewer

-0.82

audi

-0.78

oda

-0.78

anche

-0.76

utor

-0.75

ebook

-0.73

uana

-0.73

insula

-0.72

UFF

-0.71

ascript

-0.70

POSITIVE LOGITS

 Mercy

0.79

 Hers

0.69

 Herz

0.69

 Myster

0.66

lust

0.64

lessly

0.64

whel

0.64

 Lauder

0.64

 Dayton

0.63

 Britann

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.