INDEX

Explanations

expressions of gratitude and appreciation

oai_token-act-pair · gpt-3.5-turbo

references to gratitude and appreciation towards others

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

enum

-0.74

 defaults

-0.70

ageddon

-0.68

ptive

-0.68

-0.65

Elsewhere

-0.65

 modifier

-0.65

 Worse

-0.64

ivably

-0.64

 dystop

-0.63

POSITIVE LOGITS

 kindness

1.28

 generosity

1.28

 invaluable

1.27

 gracious

1.21

 generous

1.15

 kindly

1.10

 generously

1.09

 professionalism

1.07

 dedication

1.02

 thoughtful

1.02

Activations Density 1.341%

expressions of gratitude and appreciation

references to gratitude and appreciation towards others

No Comments

No Known Activations