INDEX

Explanations

acronyms related to nonprofit organizations

oai_token-act-pair · gpt-3.5-turbo

references to non-governmental organizations (NGOs)

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 recess

-0.82

Baltimore

-0.79

bleacher

-0.78

 Darrell

-0.78

 Everett

-0.77

 Stock

-0.77

 Ches

-0.76

 Madness

-0.73

 Randall

-0.73

 racks

-0.73

POSITIVE LOGITS

 NGOs

2.82

NGO

2.80

 UNHCR

2.10

 diplomat

2.08

 diplomats

1.84

 UNESCO

1.44

 multinational

1.36

MEP

1.33

WWF

1.30

IMF

1.29

Activations Density 0.032%

acronyms related to nonprofit organizations

references to non-governmental organizations (NGOs)

No Comments

No Known Activations