INDEX

Explanations

political terms and election-related mentions

oai_token-act-pair · gpt-3.5-turbo

mentions of political positions and election-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

âĹ¼

-0.88

":["

-0.77

 Countries

-0.74

 Activision

-0.73

 Europeans

-0.72

 worldwide

-0.71

 analys

-0.71

international

-0.70

Japan

-0.69

æĹ

-0.68

POSITIVE LOGITS

 gubernatorial

1.53

 runoff

1.48

bernatorial

1.39

 mayoral

1.36

 challenger

1.34

 statewide

1.34

 incumbent

1.32

 reelection

1.31

 incumb

1.29

 Democrat

1.28

Activations Density 0.607%

political terms and election-related mentions

mentions of political positions and election-related terms

No Comments

No Known Activations