INDEX

Explanations

phrases related to political ideologies advocating certain principles or values

oai_token-act-pair · gpt-3.5-turbo

concepts related to political advocacy and ideologies

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

DragonMagazine

-0.81

 Radar

-0.77

ptoms

-0.74

laughs

-0.73

 Ples

-0.72

Laughs

-0.71

wat

-0.69

adelphia

-0.68

Buzz

-0.67

 Billboard

-0.66

POSITIVE LOGITS

 equality

1.46

 neutrality

1.37

 egalitarian

1.35

 openness

1.31

 tolerance

1.30

 fairness

1.28

 moderation

1.26

clus

1.26

 abstinence

1.26

 purity

1.24

Activations Density 0.353%

phrases related to political ideologies advocating certain principles or values

concepts related to political advocacy and ideologies

No Comments

No Known Activations