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

 confir

-0.85

geries

-0.83

earable

-0.82

ailability

-0.80

anguage

-0.79

issions

-0.78

 scrut

-0.76

DonaldTrump

-0.76

ermanent

-0.72

 mathemat

-0.72

POSITIVE LOGITS

Zam

0.80

 dates

0.72

 Tart

0.64

Kop

0.63

gov

0.63

pur

0.63

 Garr

0.62

 Scholar

0.61

 Brut

0.61

 Plum

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.