INDEX

Explanations

medical conditions and related diagnoses in a text

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

soDeliveryDate

-1.20

xtap

-0.96

DragonMagazine

-0.90

selage

-0.81

Tokens

-0.81

displayText

-0.80

tarians

-0.78

Companies

-0.76

 fleets

-0.75

isSpecialOrderable

-0.73

POSITIVE LOGITS

 disease

1.73

 illness

1.63

 symptoms

1.60

 inflammation

1.58

 tuberculosis

1.57

 diseases

1.55

 illnesses

1.54

 pneumonia

1.54

 asthma

1.54

 neurological

1.53

Activations Density 1.686%

medical conditions and related diagnoses in a text

No Comments

No Known Activations