INDEX

Explanations

references to the "Star Wars" franchise

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 @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

onym

-0.93

onyms

-0.86

uckland

-0.80

iard

-0.78

ridges

-0.76

orative

-0.76

jad

-0.74

ickr

-0.73

ISON

-0.73

SPONSORED

-0.73

POSITIVE LOGITS

âĦ¢:

1.01

 Odyssey

1.00

 Awakens

0.96

âĦ¢

0.96

 Episode

0.92

 Kenobi

0.92

 Rebels

0.90

 Adventures

0.90

 trilogy

0.88

 Insider

0.88

Activations Density 0.031%

references to the "Star Wars" franchise

mentions of the "Star Wars" franchise

No Comments

No Known Activations