INDEX

Explanations

references to the Galactic Empire from the Star Wars franchise

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "Empire."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

inventoryQuantity

-0.91

gettable

-0.83

rint

-0.77

matter

-0.76

bring

-0.76

paces

-0.75

cause

-0.74

quickShipAvailable

-0.74

esters

-0.73

geoning

-0.72

POSITIVE LOGITS

 Strikes

1.13

 Empire

0.83

 State

0.82

 Polo

0.74

 Builder

0.72

wide

0.72

 Awakens

0.69

 Consolid

0.68

 outpost

0.67

 Nero

0.66

Activations Density 0.013%

references to the Galactic Empire from the Star Wars franchise

mentions of the word "Empire."

No Comments

No Known Activations