INDEX

Explanations

health-related terms and medical concepts

oai_token-act-pair · gpt-3.5-turbo

terms related to health statistics and medical assessments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

yrights

-0.85

ouver

-0.84

oil

-0.81

pload

-0.80

atron

-0.80

aunder

-0.79

assetsadobe

-0.75

Artist

-0.75

Unix

-0.74

 Bounce

-0.74

POSITIVE LOGITS

 clinical

1.24

 cardiovascular

1.24

 psychiatric

1.19

 coronary

1.16

 maternal

1.13

 clinically

1.13

 obesity

1.12

 dementia

1.11

 medication

1.10

 diabetes

1.10

Activations Density 0.413%

health-related terms and medical concepts

terms related to health statistics and medical assessments

No Comments

No Known Activations