INDEX

Explanations

medical terms and descriptions in a hospital setting

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

angular

-0.79

oras

-0.74

OPA

-0.72

argon

-0.69

 Dunk

-0.68

ãĥ©ãĥ³

-0.68

ģ«

-0.64

gers

-0.63

ordan

-0.63

ball

-0.62

POSITIVE LOGITS

 patients

1.07

 patient

0.98

ients

0.95

 Patients

0.94

ysis

0.91

 hospitalized

0.90

 diagnosed

0.90

killer

0.87

 suffering

0.85

 undergoing

0.83

Activations Density 0.033%

medical terms and descriptions in a hospital setting

No Comments

No Known Activations