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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Alic

-0.73

rom

-0.67

 Crusader

-0.67

Stud

-0.67

 Frankfurt

-0.65

 Ronaldo

-0.64

annis

-0.64

Cyn

-0.63

 conclud

-0.62

 Stud

-0.62

POSITIVE LOGITS

pees

0.83

apor

0.80

pee

0.78

ergic

0.72

hare

0.70

umatic

0.68

 tasted

0.66

etsy

0.66

keleton

0.65

zn

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.