INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

fen

-0.69

 Inqu

-0.66

dra

-0.63

 Rwanda

-0.60

 ãĤµ

-0.59

 Phant

-0.59

nz

-0.59

nah

-0.58

 dest

-0.57

cro

-0.57

POSITIVE LOGITS

BuyableInstoreAndOnline

0.76

quickShipAvailable

0.75

ovember

0.73

esity

0.68

 Temperature

0.66

behavior

0.65

inventoryQuantity

0.65

 è£ıè

0.65

share

0.64

hatt

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.