INDEX

Explanations

words related to Zen philosophy and technology

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

 Lauder

-0.71

RAG

-0.65

 mileage

-0.63

 organized

-0.63

 encour

-0.63

 misc

-0.62

Md

-0.61

WD

-0.61

âĢ¢âĢ¢âĢ¢âĢ¢

-0.61

 Bagg

-0.60

POSITIVE LOGITS

obia

1.31

eca

1.24

ith

1.20

obi

1.08

iths

1.00

ica

0.89

ipal

0.88

pei

0.87

icol

0.87

ealous

0.86

Activations Density 0.027%

words related to Zen philosophy and technology

No Comments

No Known Activations