INDEX

Explanations

references to popular science fiction franchises

oai_token-act-pair · gpt-3.5-turbo

mentions of the "Star Wars" franchise

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

Downloadha

-0.90

utics

-0.86

LIA

-0.86

terday

-0.85

sembly

-0.83

£ı

-0.82

 confir

-0.82

pse

-0.79

 Canaver

-0.78

xual

-0.78

POSITIVE LOGITS

light

1.08

 Trek

1.05

 Wars

0.99

buck

0.96

burst

0.92

Wars

0.89

liner

0.88

lite

0.88

 Citizen

0.87

ring

0.86

Activations Density 0.021%

references to popular science fiction franchises

mentions of the "Star Wars" franchise

No Comments

No Known Activations