INDEX

Explanations

mentions of political figures and legal actions

oai_token-act-pair · gpt-3.5-turbo

topics related to legal issues and criminal activities

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

 Croatian

-0.93

MX

-0.85

 Sinai

-0.83

stanbul

-0.81

 Serbian

-0.79

 Istanbul

-0.79

Kos

-0.79

Gim

-0.79

 Yugoslav

-0.79

 Croatia

-0.79

POSITIVE LOGITS

 Warren

2.67

Warren

2.54

 Elizabeth

1.52

Elizabeth

1.35

 Buffett

1.22

 Dodd

1.21

 Berkshire

1.20

 Massachusetts

1.12

 Vanguard

1.06

 Sanders

1.05

Activations Density 0.163%

mentions of political figures and legal actions

topics related to legal issues and criminal activities

No Comments

No Known Activations