INDEX

Explanations

names of countries around the world

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Pru

-0.80

getic

-0.79

kson

-0.79

sburgh

-0.75

assetsadobe

-0.73

 TODAY

-0.71

 captcha

-0.68

 Rough

-0.64

 Lauder

-0.63

à©

-0.63

POSITIVE LOGITS

peria

1.21

avier

1.19

posed

1.15

yz

1.10

aminer

1.01

anth

1.00

ternal

0.97

pert

0.91

ample

0.89

eno

0.89

Activations Density 0.494%

names of countries around the world

No Comments

No Known Activations