INDEX

Explanations

anatomy-related terms, especially relating to specific body parts and medical procedures

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

 Atmosp

-0.85

DEM

-0.78

 Outbreak

-0.76

actionDate

-0.74

Ans

-0.74

MQ

-0.72

 Soda

-0.69

ÃįÃį

-0.69

 Flavoring

-0.68

oday

-0.67

POSITIVE LOGITS

 circumference

1.36

 cavity

1.12

 diameter

1.07

bones

1.06

bone

1.05

 protr

1.02

 muscles

1.01

 lobe

0.98

 shaft

0.98

 bones

0.96

Activations Density 0.145%

anatomy-related terms, especially relating to specific body parts and medical procedures

No Comments

No Known Activations