INDEX

Explanations

specific references to technology products or components

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

Cause

-0.85

ERROR

-0.81

Population

-0.80

URI

-0.77

crime

-0.76

Crime

-0.76

 contagious

-0.75

Political

-0.74

 contag

-0.73

istical

-0.73

POSITIVE LOGITS

 Panasonic

1.11

 Yamaha

1.10

 Samsung

1.01

 Asus

1.00

 Motorola

0.99

 Garmin

0.98

 Jaguar

0.98

RX

0.96

 Model

0.95

 ASUS

0.95

Activations Density 0.296%

specific references to technology products or components

No Comments

No Known Activations