INDEX

Explanations

technical terms related to information technology and security, such as uptime, database, security breaches, technology capabilities, and server commands

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt

Prompts (Dashboard)

12,288 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

46,080

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

apollo-research/Skylion007-openwebtext-tokenizer-gpt2

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĤ©

-1.30

natureconservancy

-1.29

sylv

-1.26

etsk

-1.21

uliffe

-1.15

 constitu

-1.13

urally

-1.11

sylvania

-1.09

 ingred

-1.06

achu

-1.06

POSITIVE LOGITS

hour

1.06

hours

1.03

eve

0.99

PsyNetMessage

0.92

0.91

0.90

Activations Density 1.602%

technical terms related to information technology and security, such as uptime, database, security breaches, technology capabilities, and server commands

No Comments

No Known Activations