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

MB

-0.68

tern

-0.66

realDonaldTrump

-0.64

 Quadro

-0.63

license

-0.63

uckle

-0.63

adden

-0.62

rette

-0.62

oute

-0.62

bos

-0.61

POSITIVE LOGITS

 scrut

0.76

 mosqu

0.74

 Hallow

0.72

0.69

 distingu

0.68

 Palestin

0.68

pse

0.66

»Ĵ

0.64

Sew

0.64

 surv

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.