INDEX

Explanations

references to specific brands, products, or locations

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

aunts

-0.76

 manif

-0.66

 flank

-0.64

 manifold

-0.62

trap

-0.62

 millionaires

-0.61

gui

-0.61

gap

-0.59

ploy

-0.59

asks

-0.59

POSITIVE LOGITS

 copyrighted

1.06

 trademarks

1.01

 copyright

0.98

 affiliate

0.94

 editorial

0.89

çīĪ

0.87

Disclaimer

0.86

 Contribut

0.82

 Copyright

0.82

 Attribution

0.82

Activations Density 1.734%

references to specific brands, products, or locations

No Comments

No Known Activations