INDEX

Explanations

words related to specific software programs and technology brands

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

arios

-0.98

aries

-0.94

icles

-0.73

ablishment

-0.73

erest

-0.73

ourced

-0.71

erva

-0.71

ocre

-0.71

ander

-0.70

obos

-0.70

POSITIVE LOGITS

 Photoshop

1.00

RGB

0.85

Plex

0.81

MAT

0.80

AIR

0.79

 Reader

0.77

 Illust

0.77

Â®

0.76

Ac

0.76

Commerce

0.75

Activations Density 0.025%

words related to specific software programs and technology brands

No Comments

No Known Activations