INDEX

Explanations

technical information related to software development and management

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ornia

-0.74

awei

-0.73

keyes

-0.72

achelor

-0.70

sonian

-0.70

amy

-0.70

keye

-0.69

urst

-0.68

jamin

-0.68

clad

-0.65

POSITIVE LOGITS

xual

1.14

geist

1.05

itions

1.02

itory

0.95

itional

0.89

itor

0.80

itionally

0.79

itives

0.78

ktop

0.78

 Tackle

0.77

Activations Density 8.555%

technical information related to software development and management

No Comments

No Known Activations