INDEX

Explanations

medical terms and symptoms

oai_token-act-pair · gpt-3.5-turbo

terms related to medical symptoms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 Citiz

-0.79

PDATE

-0.78

Offline

-0.73

Versions

-0.72

 tremend

-0.72

luck

-0.70

ropolitan

-0.69

ailability

-0.68

inventoryQuantity

-0.66

DragonMagazine

-0.65

POSITIVE LOGITS

 Uruguay

0.67

eer

0.66

tek

0.64

psey

0.64

tab

0.63

zza

0.62

ogun

0.61

cam

0.61

 cent

0.60

Naz

0.60

Activations Density 0.000%

medical terms and symptoms

terms related to medical symptoms

No Comments

No Known Activations