INDEX

Explanations

descriptions of famous landmarks and buildings

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

 subsequent

-0.68

 psychiat

-0.66

 comprom

-0.66

ttle

-0.64

 charact

-0.63

 grandchildren

-0.63

xual

-0.61

mberg

-0.61

 complying

-0.61

 obstruction

-0.60

POSITIVE LOGITS

advertising

1.17

 Located

1.01

Probably

0.90

Legendary

0.84

 Seriously

0.78

Located

0.78

 Probably

0.77

 Another

0.77

 Released

0.77

Eas

0.76

Activations Density 1.378%

descriptions of famous landmarks and buildings

No Comments

No Known Activations