INDEX

Explanations

medical symptoms and conditions

oai_token-act-pair · gpt-3.5-turbo

phrases related to health conditions and their implications

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Untitled

-0.81

ãĥķãĤ©

-0.71

azon

-0.70

Lenin

-0.69

Render

-0.68

$$

-0.68

 Legions

-0.68

 Honour

-0.67

Marx

-0.67

 Roku

-0.66

POSITIVE LOGITS

 Symptoms

1.08

 protective

0.96

 medications

0.95

 nutritional

0.95

 dietary

0.95

 calcium

0.90

healthy

0.90

 therapeutic

0.90

 symptoms

0.89

 potassium

0.89

Activations Density 1.060%

medical symptoms and conditions

phrases related to health conditions and their implications

No Comments

No Known Activations