INDEX

Explanations

quotations and statements within quotation marks

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

 Ross

-0.78

 derby

-0.73

 rall

-0.72

 Creator

-0.70

 Story

-0.70

 affiliate

-0.69

Yam

-0.69

 calendar

-0.69

 Isaac

-0.69

 rental

-0.68

POSITIVE LOGITS

absolutely

1.56

completely

1.48

very

1.47

almost

1.43

probably

1.43

extremely

1.42

significant

1.42

every

1.39

pretty

1.39

clear

1.38

Activations Density 0.316%

quotations and statements within quotation marks

No Comments

No Known Activations