INDEX

Explanations

HTML tags and attributes

oai_token-act-pair · gpt-3.5-turbo

equal signs and their associated values, indicating variable assignments or data configurations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Coat

-0.70

 pointing

-0.70

 breed

-0.68

 coat

-0.67

 Divide

-0.67

 limp

-0.65

 casting

-0.65

 Reserv

-0.64

 Contra

-0.64

 Karin

-0.64

POSITIVE LOGITS

ãĥīãĥ©ãĤ´ãĥ³

1.22

true

1.16

False

1.10

ãĥ´ãĤ¡

1.08

false

1.06

Abstract

1.06

CVE

1.05

True

1.04

PsyNetMessage

1.03

Activations Density 0.021%

HTML tags and attributes

equal signs and their associated values, indicating variable assignments or data configurations

No Comments

No Known Activations