INDEX

Explanations

terms related to medical imaging

oai_token-act-pair · gpt-3.5-turbo

terms related to imaging technology

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.3.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

cake

-0.89

unin

-0.83

bare

-0.73

steen

-0.71

cker

-0.70

bread

-0.70

chant

-0.69

hands

-0.68

ivari

-0.66

egg

-0.66

POSITIVE LOGITS

 imaging

1.04

 microsc

0.97

 scanners

0.87

 Imaging

0.86

 sickness

0.84

 scans

0.84

 visuals

0.80

 projector

0.80

 visualize

0.79

 capabilities

0.78

Activations Density 0.013%

terms related to medical imaging

terms related to imaging technology

No Comments

No Known Activations