INDEX

Explanations

mentions of the term "Star" followed by a single digit

oai_token-act-pair · gpt-3.5-turbo

references to the "Star" franchise, specifically "Star Wars" and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

terday

-0.93

utics

-0.84

ongyang

-0.83

sembly

-0.82

ipop

-0.80

LIA

-0.79

ascript

-0.76

£ı

-0.75

pse

-0.75

ecause

-0.74

POSITIVE LOGITS

light

1.09

 Trek

1.00

vation

0.99

buck

0.99

 Wars

0.97

ring

0.97

burst

0.97

fish

0.94

bucks

0.86

Wars

0.86

Activations Density 0.030%

mentions of the term "Star" followed by a single digit

references to the "Star" franchise, specifically "Star Wars" and related terms

No Comments

No Known Activations