INDEX

Explanations

words related to health, such as specific medical terms, conditions, and treatments

oai_token-act-pair · gpt-3.5-turbo

items and concepts related to health and lifestyle factors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

atters

-0.52

 Canaver

-0.50

DragonMagazine

-0.49

ossier

-0.47

MpServer

-0.47

natureconservancy

-0.46

 partName

-0.46

 Supervisor

-0.46

 Originally

-0.45

 Kamp

-0.45

POSITIVE LOGITS

.''.

1.17

.(

1.06

.[

1.04

*.

1.03

.ï¿½

1.02

.</

1.00

+.

0.99

!.

0.98

.<

0.95

0.94

Activations Density 1.002%

words related to health, such as specific medical terms, conditions, and treatments

items and concepts related to health and lifestyle factors

No Comments

No Known Activations