INDEX

Explanations

phrases related to political ideologies or movements, particularly those involving Islam

oai_token-act-pair · gpt-3.5-turbo

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Cosponsors

-1.04

 anecd

-0.89

 anecdotes

-0.80

 anecdotal

-0.76

visors

-0.73

 Advisory

-0.72

 commenters

-0.71

comments

-0.71

 Mermaid

-0.70

 Volunte

-0.70

POSITIVE LOGITS

 hegemony

1.33

 conquest

1.27

 communism

1.22

 domination

1.22

 tyranny

1.21

 revenge

1.20

 jihad

1.18

 Communism

1.18

 overthrow

1.16

 Islam

1.15

Activations Density 0.426%

phrases related to political ideologies or movements, particularly those involving Islam

No Comments

No Known Activations