INDEX

Explanations

historical events or figures

oai_token-act-pair · gpt-3.5-turbo

sentences that suggest a high degree of importance or significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 mandate

-0.85

 freel

-0.85

 sprint

-0.84

 proactive

-0.81

 tackling

-0.81

 assurance

-0.81

 crunch

-0.81

 blocker

-0.81

 testing

-0.80

 priorit

-0.80

POSITIVE LOGITS

Contents

1.65

History

1.63

During

1.57

Years

1.56

Born

1.54

References

1.51

Between

1.49

Appearances

1.48

Newsletter

1.48

Advertisements

1.48

Activations Density 0.512%

historical events or figures

sentences that suggest a high degree of importance or significance

No Comments

No Known Activations