INDEX

Explanations

terms related to medical imaging, experimental design, and medical conditions

oai_token-act-pair · gpt-3.5-turbo

references to medical studies involving treated subjects and their evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

Politics

-0.82

HCR

-0.80

tions

-0.79

 Ideas

-0.79

THING

-0.77

rency

-0.77

 meanings

-0.77

INESS

-0.75

 amenities

-0.72

 Gathering

-0.72

POSITIVE LOGITS

 mice

1.43

 patients

1.42

 diabetic

1.31

 obese

1.26

 Patients

1.25

 rats

1.25

 infants

1.15

 adolescents

1.15

 monkeys

1.12

 smokers

1.12

Activations Density 0.268%

terms related to medical imaging, experimental design, and medical conditions

references to medical studies involving treated subjects and their evaluations

No Comments

No Known Activations