INDEX

Explanations

philosophical arguments and academic references

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

 bragging

-0.67

 chanted

-0.64

interstitial

-0.62

VALUE

-0.62

Outside

-0.62

oaded

-0.61

 unlocked

-0.60

 broadcasting

-0.60

inventoryQuantity

-0.60

 orally

-0.59

POSITIVE LOGITS

et

1.41

 supra

1.20

aceae

0.87

 Handbook

0.86

itsch

0.85

 Associates

0.83

JA

0.83

DOI

0.80

 Encyclopedia

0.79

pp

0.78

Activations Density 0.862%

philosophical arguments and academic references

No Comments

No Known Activations