INDEX

Explanations

information related to policies, regulations, and statements by government officials

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

 quot

-1.03

 puberty

-0.98

 fuckin

-0.97

 barr

-0.94

 cram

-0.91

 dirt

-0.90

 exorc

-0.89

gul

-0.89

 bunker

-0.88

 Saiyan

-0.88

POSITIVE LOGITS

Our

1.37

We

1.33

Technology

1.32

Develop

1.24

Working

1.24

Effective

1.23

This

1.23

Unfortunately

1.20

Stars

1.18

Trust

1.16

Activations Density 0.830%

information related to policies, regulations, and statements by government officials

No Comments

No Known Activations