INDEX

Explanations

specific locations or addresses

oai_token-act-pair · gpt-3.5-turbo

specific addresses and location descriptions

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 rehe

-0.76

NPR

-0.67

 unheard

-0.66

lessness

-0.66

 hiber

-0.66

 autobiography

-0.65

Japan

-0.65

 organising

-0.64

 homebrew

-0.63

 unmatched

-0.63

POSITIVE LOGITS

 Avenue

1.70

 Blvd

1.63

 Boulevard

1.55

Ave

1.55

Rd

1.50

 Street

1.49

 Highway

1.37

 Road

1.36

 avenue

1.36

 Drive

1.30

Activations Density 0.216%

specific locations or addresses

specific addresses and location descriptions

No Known Activations