INDEX

Explanations

phrases signaling continuation or action

oai_token-act-pair · gpt-3.5-turbo

end punctuation marks, particularly periods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 credential

-0.86

 inund

-0.78

 occupancy

-0.77

 transact

-0.75

 discern

-0.71

 plurality

-0.71

 unman

-0.71

 disrupt

-0.71

 unaff

-0.70

 lawyers

-0.69

POSITIVE LOGITS

 Anyway

1.42

 Lastly

1.32

Anyway

1.30

;)

1.29

 Hopefully

1.27

↵Âł

1.27

 Also

1.26

:)

1.25

 Enjoy

1.19

 Firstly

1.18

Activations Density 0.388%

phrases signaling continuation or action

end punctuation marks, particularly periods

No Comments

No Known Activations