INDEX

Explanations

medically related words and symptoms

oai_token-act-pair · gpt-3.5-turbo

terms related to medical conditions and their management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Franch

-0.86

selage

-0.74

 Transparency

-0.73

Brook

-0.73

 Bezos

-0.73

 Voting

-0.71

 Franchise

-0.70

 Publishers

-0.70

yrights

-0.70

Flags

-0.69

POSITIVE LOGITS

 symptoms

1.49

 hormonal

1.37

 medication

1.33

 medications

1.31

 symptom

1.30

 hormone

1.28

 inflammation

1.28

 Symptoms

1.28

 physiological

1.24

 therapeutic

1.23

Activations Density 0.859%

medically related words and symptoms

terms related to medical conditions and their management

No Comments

No Known Activations