INDEX

Explanations

medical research-related terms and statistical analysis terms

oai_token-act-pair · gpt-3.5-turbo

terms related to health data analysis and methodology in research studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

leaf

-0.76

 trillions

-0.71

ojure

-0.67

wx

-0.65

grow

-0.65

Lago

-0.65

xit

-0.65

etc

-0.64

crete

-0.64

 boils

-0.63

POSITIVE LOGITS

 questionnaire

1.08

 Participants

0.91

 investigator

0.91

 participant

0.89

 Investigator

0.87

 dataset

0.86

 statistical

0.86

 Subjects

0.84

 cohort

0.83

 validated

0.82

Activations Density 0.168%

medical research-related terms and statistical analysis terms

terms related to health data analysis and methodology in research studies

No Comments

No Known Activations