INDEX

Explanations

names of politicians and universities

oai_token-act-pair · gpt-3.5-turbo

abbreviated names and acronyms related to organizations or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

thood

-0.68

DragonMagazine

-0.67

 Carnage

-0.65

 Paras

-0.63

 Canaver

-0.63

 Carbuncle

-0.61

xual

-0.61

Aph

-0.60

 repatri

-0.58

 Kubrick

-0.58

POSITIVE LOGITS

nesota

1.12

erville

1.11

adelphia

1.11

neapolis

1.03

mington

1.02

esville

1.02

ansas

1.00

achusetts

0.99

anooga

0.99

aukee

0.97

Activations Density 0.293%

names of politicians and universities

abbreviated names and acronyms related to organizations or entities

No Comments

No Known Activations