INDEX

Explanations

numeric quantities

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

 Caption

-0.68

ned

-0.62

gall

-0.61

rike

-0.57

ered

-0.54

erers

-0.54

cheat

-0.53

ibel

-0.52

GA

-0.52

quartered

-0.52

POSITIVE LOGITS

 reasons

1.22

 sake

1.21

 purposes

1.20

 awhile

1.02

 eternity

1.00

 duration

0.98

 years

0.95

 periods

0.94

ummies

0.94

 hours

0.92

Activations Density 0.189%

numeric quantities

No Comments

No Known Activations