INDEX

Explanations

medical terms related to diagnostic imaging such as MRI and procedures such as ultrasound and autopsy

oai_token-act-pair · gpt-3.5-turbo

terms related to medical imaging and examinations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

ãĤ±

-0.74

ivil

-0.72

 evasion

-0.72

chie

-0.71

 pursu

-0.71

 diversion

-0.71

pled

-0.70

Dod

-0.69

lement

-0.69

anna

-0.68

POSITIVE LOGITS

MRI

3.12

MRI

2.64

 ultrasound

2.31

 autopsy

2.12

 microscope

1.74

 microsc

1.63

opsy

1.54

 anatomical

1.46

 imaging

1.42

 Ultr

1.40

Activations Density 0.048%

medical terms related to diagnostic imaging such as MRI and procedures such as ultrasound and autopsy

terms related to medical imaging and examinations

No Comments

No Known Activations