INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.8.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

BuyableInstoreAndOnline

-0.64

ÃŁ

-0.59

FML

-0.57

ibrary

-0.56

igate

-0.55

 Liga

-0.55

Ã¡s

-0.54

 Leave

-0.54

 Serie

-0.54

 Albany

-0.54

POSITIVE LOGITS

 accordingly

1.50

 thereafter

1.25

 thereof

1.21

 therein

1.18

 consequently

1.13

 alike

1.12

 thereto

1.04

 ensued

0.91

 afterward

0.90

 versa

0.90

Activations Density 0.616%

proper nouns

No Comments

No Known Activations