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

å§«

-0.94

wcs

-0.89

anship

-0.74

erity

-0.74

DragonMagazine

-0.74

itsch

-0.71

 istg

-0.70

nv

-0.69

ogun

-0.68

£ı

-0.68

POSITIVE LOGITS

 IEEE

0.69

 Quiet

0.67

Loc

0.64

lees

0.63

expected

0.62

 Merry

0.61

worldly

0.60

 Neigh

0.59

 Hilbert

0.58

TLS

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.