INDEX

Explanations

names of specific entities or individuals

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

enegger

-0.50

anwhile

-0.46

 Niet

-0.43

 Vaugh

-0.40

çīĪ

-0.38

 Thumbnails

-0.37

*.

-0.37

srf

-0.36

lished

-0.36

 prest

-0.36

POSITIVE LOGITS

coin

0.53

Coin

0.50

ratom

0.44

ÂŃ

0.43

rock

0.40

 âĢº

0.38

âĢĲ

0.37

Â¶

0.37

Boss

0.36

ython

0.36

Activations Density 7.459%

names of specific entities or individuals

No Comments

No Known Activations