INDEX

Explanations

phrases related to opposing projects or ideas

oai_token-act-pair · gpt-3.5-turbo

punctuation and line breaks within the text

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

 Coun

-0.83

Oo

-0.72

 Overt

-0.68

 altern

-0.68

 Pigs

-0.67

Sov

-0.67

 photograp

-0.67

 anecd

-0.66

 mull

-0.66

 grop

-0.66

POSITIVE LOGITS

Topics

1.15

Related

1.14

Copyright

1.13

Share

1.10

Date

1.10

Hide

1.10

Latest

1.10

Information

1.10

Disclaimer

1.08

Contribut

1.08

Activations Density 0.122%

phrases related to opposing projects or ideas

punctuation and line breaks within the text

No Comments

No Known Activations