INDEX

Explanations

medical terms and phrases related to healthcare issues

oai_token-act-pair · gpt-3.5-turbo

conjunctions and phrases indicating a variety of subjects or factors in relation to health-related discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

arde

-0.76

orem

-0.72

eur

-0.70

¬¼

-0.68

ISION

-0.67

cker

-0.63

enary

-0.63

Į

-0.61

uni

-0.60

irst

-0.60

POSITIVE LOGITS

 including

1.69

including

1.30

 namely

1.28

 Including

1.26

 includ

1.23

 ranging

1.12

 notably

1.11

 albeit

1.04

 besides

1.01

 respectively

1.00

Activations Density 0.446%

medical terms and phrases related to healthcare issues

conjunctions and phrases indicating a variety of subjects or factors in relation to health-related discussions

No Comments

No Known Activations