INDEX

Explanations

political terms and names

oai_token-act-pair · gpt-3.5-turbo

phrases related to political discourse or commentary

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

âĢ

-1.01

ãĥŁ

-0.98

VERTISEMENT

-0.93

ãĤ¨ãĥ«

-0.88

obyl

-0.87

 âĢ

-0.85

advertisement

-0.85

âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ

-0.83

ãĤ©

-0.83

ãĢ

-0.82

POSITIVE LOGITS

 Democrats

1.45

 Republicans

1.44

 Obama

1.40

 Hillary

1.38

 Barack

1.36

Republicans

1.32

 AMERICA

1.30

 progressives

1.29

 liberals

1.29

 Dems

1.28

Activations Density 0.856%

political terms and names

phrases related to political discourse or commentary

No Comments

No Known Activations