INDEX

Explanations

noun-verb pairs related to conflict or competition

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

mos

-0.69

 Defenders

-0.63

pod

-0.63

NESS

-0.60

 silence

-0.59

 loan

-0.59

 Confederacy

-0.58

 Wilde

-0.58

wives

-0.58

quo

-0.57

POSITIVE LOGITS

inators

1.31

inator

1.24

inational

1.23

inatory

1.18

ative

1.11

ats

1.08

inations

1.00

enhagen

0.95

xon

0.94

uations

0.94

Activations Density 0.025%

noun-verb pairs related to conflict or competition

No Comments

No Known Activations