INDEX

Explanations

instructions or steps in a guide or recipe

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

.).

-0.55

).[

-0.54

."[

-0.53

]."

-0.52

.'"

-0.50

.ï¿½

-0.49

)."

-0.48

.''.

-0.47

".[

-0.46

.''

-0.45

POSITIVE LOGITS

resa

0.32

arij

0.30

ividual

0.29

izontal

0.29

reenshots

0.28

zens

0.28

Picture

0.27

atform

0.27

iquette

0.27

terday

0.27

Activations Density 3.669%

instructions or steps in a guide or recipe

No Comments

No Known Activations