INDEX

Explanations

special characters used in a specific context

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

Led

-0.82

 Cassidy

-0.79

 Dickinson

-0.74

 Barron

-0.70

ulhu

-0.68

 Loll

-0.68

 Reloaded

-0.68

WD

-0.68

 Rivals

-0.66

Kyl

-0.66

POSITIVE LOGITS

existent

1.42

government

1.32

special

1.23

division

1.23

exclusive

1.20

dist

1.20

national

1.19

conf

1.19

sent

1.18

cont

1.18

Activations Density 0.416%

special characters used in a specific context

No Comments

No Known Activations