INDEX

Explanations

phrases or excerpts that are used to summarize or provide an overview of a situation or event

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate summarization or conclusion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 booted

-0.65

ometers

-0.63

PAC

-0.62

ometer

-0.62

grounds

-0.62

 footing

-0.60

hement

-0.59

 inhibitor

-0.59

 certific

-0.58

entimes

-0.57

POSITIVE LOGITS

Quotes

0.87

 quotes

0.75

 phrases

0.73

 quotation

0.71

 pronoun

0.69

 concise

0.69

ript

0.68

 succinct

0.68

 pertinent

0.67

 quotations

0.66

Activations Density 0.471%

phrases or excerpts that are used to summarize or provide an overview of a situation or event

phrases that indicate summarization or conclusion

No Comments

No Known Activations