INDEX

Explanations

software code strings and instructions related to coding and data validation in a computer program

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ĸļ

-1.18

 reconc

-0.93

 malls

-0.92

 mouths

-0.90

 galleries

-0.88

liam

-0.87

 dotted

-0.86

edin

-0.83

dale

-0.81

 anchors

-0.79

POSITIVE LOGITS

osi

0.99

ulence

0.92

 Applic

0.91

properties

0.87

viation

0.86

 Imper

0.85

smanship

0.84

 Except

0.83

 Odin

0.81

inctions

0.81

Activations Density 1.904%

software code strings and instructions related to coding and data validation in a computer program

No Comments

No Known Activations