INDEX

Explanations

words related to narrating stories and characters in the context of filmmaking

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

 credential

-0.95

 authorized

-0.92

 legally

-0.92

 entitle

-0.88

 legal

-0.86

 lease

-0.86

 prepaid

-0.86

 advis

-0.85

 voluntarily

-0.84

 lawfully

-0.83

POSITIVE LOGITS

 Characters

1.46

 Scenes

1.38

 Whereas

1.35

 Featuring

1.31

Characters

1.31

 Throughout

1.25

 Subtle

1.22

 Regardless

1.21

 Though

1.21

 Whether

1.20

Activations Density 0.334%

words related to narrating stories and characters in the context of filmmaking

No Comments

No Known Activations