INDEX

Explanations

code snippets and technical documentation related to programming topics

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

 Beir

-0.96

 spons

-0.94

ierrez

-0.91

 ultras

-0.89

 Confeder

-0.84

 Hels

-0.83

odynam

-0.79

ussen

-0.76

anooga

-0.74

accompan

-0.74

POSITIVE LOGITS

1.38

00000000

1.26

1.24

1.22

1.21

1.18

1.17

1.16

 bytes

1.12

Activations Density 14.301%

code snippets and technical documentation related to programming topics

No Comments

No Known Activations