INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

Tyr

-0.79

 reserve

-0.72

 Laure

-0.72

 moder

-0.68

 typew

-0.67

 Creed

-0.66

emn

-0.64

 foss

-0.63

hammer

-0.62

 Serge

-0.62

POSITIVE LOGITS

inventoryQuantity

0.87

nown

0.85

Sensor

0.80

azaki

0.80

iscons

0.79

YY

0.77

soDeliveryDate

0.76

opian

0.76

»Ĵ

0.75

oldown

0.71

Activations Density 0.000%

No Known Activations

This feature has no known activations.