INDEX

Explanations

acronyms and initials

oai_token-act-pair · gpt-3.5-turbo

terms related to acronyms and abbreviations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

Peb

-0.72

Cu

-0.70

nder

-0.69

ebook

-0.69

Live

-0.68

 Diver

-0.66

taboola

-0.65

 Wynne

-0.64

 Hannity

-0.64

 Blasio

-0.62

POSITIVE LOGITS

 acronym

1.33

 abbre

1.17

viation

1.15

 abbrevi

1.08

 acron

1.08

 initials

1.04

 jargon

0.89

 aliases

0.89

 moniker

0.85

 notation

0.82

Activations Density 0.008%

acronyms and initials

terms related to acronyms and abbreviations

No Comments

No Known Activations