INDEX

Explanations

quotations

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

 encl

-0.79

 casc

-0.78

 popul

-0.76

 termin

-0.76

 subsidies

-0.72

civ

-0.70

 subsid

-0.69

 erosion

-0.68

 privat

-0.68

 overfl

-0.67

POSITIVE LOGITS

Yeah

1.41

Obviously

1.30

Honestly

1.26

Everybody

1.25

Coach

1.22

Absolutely

1.20

Very

1.12

Yes

1.11

Certainly

1.11

Probably

1.11

Activations Density 0.091%

quotations

No Comments

No Known Activations