INDEX

Explanations

technical medical terms and measurements

oai_token-act-pair · gpt-3.5-turbo

statistical terms and concepts related to health outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 rooft

-0.68

Lago

-0.67

Planet

-0.64

 Paradise

-0.63

atron

-0.63

ãĥķãĤ©

-0.62

ãĥ´ãĤ¡

-0.62

ouver

-0.62

Throw

-0.60

Knight

-0.59

POSITIVE LOGITS

 clinically

0.99

 biomark

0.99

alyses

0.98

 phenotype

0.96

 heterogeneity

0.96

 genomic

0.93

 analges

0.93

 serum

0.91

 lipid

0.90

 clinical

0.90

Activations Density 1.577%

technical medical terms and measurements

statistical terms and concepts related to health outcomes

No Comments

No Known Activations