INDEX

Explanations

hashtags used for social media topics

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

 foremost

-0.76

 Gors

-0.73

 Sylv

-0.72

 convers

-0.70

 destro

-0.70

oun

-0.68

 Ambrose

-0.66

 tabl

-0.66

Vie

-0.66

 slips

-0.65

POSITIVE LOGITS

define

1.34

################################

1.26

DIV

1.23

!/

1.18

include

1.17

########

1.11

Gamer

1.08

################

1.03

DonaldTrump

1.03

RIP

1.03

Activations Density 0.878%

hashtags used for social media topics

No Comments

No Known Activations