INDEX

Explanations

words related to technical issues, security breaches, and legislative actions

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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

Redd

-0.34

hem

-0.33

amaz

-0.32

DIV

-0.32

Export

-0.30

poke

-0.28

mine

-0.27

###

-0.27

hed

-0.27

olds

-0.27

POSITIVE LOGITS

aries

0.48

istic

0.47

ist

0.45

istically

0.45

naire

0.44

ists

0.43

IST

0.42

atively

0.39

ative

0.37

ally

0.37

Activations Density 7.178%

words related to technical issues, security breaches, and legislative actions

No Comments

No Known Activations