INDEX

Explanations

phrases related to legal terms and regulations

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_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

gery

-0.80

 Ended

-0.66

 downed

-0.64

 aloud

-0.64

 purchases

-0.63

 speeches

-0.62

 lawy

-0.61

mates

-0.61

 overcame

-0.60

 footage

-0.59

POSITIVE LOGITS

 category

1.08

 realm

0.93

 categories

0.90

Interstitial

0.89

category

0.87

BuyableInstoreAndOnline

0.86

 spectrum

0.85

ĪĴ

0.84

 continuum

0.82

auntlet

0.81

Activations Density 0.196%

phrases related to legal terms and regulations

No Comments

No Known Activations