INDEX

Explanations

descriptive words related to physical locations and landmarks

oai_token-act-pair · gpt-3.5-turbo

phrases related to scenic views and outdoor activities

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

 implanted

-0.88

 implant

-0.86

 implants

-0.86

 chromosomes

-0.81

 wrongful

-0.81

 patent

-0.78

 chromosome

-0.78

 epigen

-0.76

 surg

-0.76

 genetically

-0.76

POSITIVE LOGITS

 scenic

1.08

 attractions

1.02

 hotels

1.00

 tourist

0.99

 tourists

0.95

 downtown

0.94

 Restaur

0.94

 Tours

0.91

 Downtown

0.91

 booking

0.90

Activations Density 0.653%

descriptive words related to physical locations and landmarks

phrases related to scenic views and outdoor activities

No Comments

No Known Activations