INDEX

Explanations

proper nouns and specific terms with mixed importance

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

 Tags

-0.79

 Grants

-0.74

 Dreams

-0.68

 Solitaire

-0.65

ĺħ

-0.65

 Analytics

-0.64

 Advice

-0.63

 GEAR

-0.63

 Projects

-0.62

 Jackets

-0.62

POSITIVE LOGITS

famous

0.97

 lucrative

0.95

 elaborate

0.94

 diverse

0.94

 prestigious

0.92

 sophisticated

0.92

 expansive

0.92

 disparate

0.90

 illustrious

0.89

 intricate

0.88

Activations Density 1.987%

proper nouns and specific terms with mixed importance

No Comments

No Known Activations