INDEX

Explanations

mentions related to mindfulness

oai_token-act-pair · gpt-3.5-turbo

concepts related to mindfulness and well-being

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

-0.88

eways

-0.87

adium

-0.74

ional

-0.72

parts

-0.70

hips

-0.70

ulas

-0.70

 Stall

-0.69

Ford

-0.68

inian

-0.68

POSITIVE LOGITS

 mindfulness

1.18

 meditation

1.02

fulness

0.96

 mindful

0.95

 Meditation

0.92

 pract

0.74

issance

0.73

 contempl

0.72

 minded

0.72

nsic

0.71

Activations Density 0.016%

mentions related to mindfulness

concepts related to mindfulness and well-being

No Comments

No Known Activations