INDEX

Explanations

phrases related to hotels, resorts, and hotel chains

oai_token-act-pair · gpt-3.5-turbo

references to hotels

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

*/(

-0.79

ebook

-0.73

lang

-0.71

ean

-0.70

rd

-0.70

owder

-0.67

gotten

-0.65

itives

-0.64

printed

-0.63

unders

-0.63

POSITIVE LOGITS

 Hotel

1.37

 Marriott

0.91

 Restaur

0.90

 hotel

0.90

 hotels

0.89

 Rooms

0.89

 Royale

0.81

 Hilton

0.80

Hot

0.79

 Plaza

0.78

Activations Density 0.010%

phrases related to hotels, resorts, and hotel chains

references to hotels

No Comments

No Known Activations