INDEX

Explanations

legal and policy-related terms

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

affe

-0.90

Geh

-0.89

 Able

-0.87

hack

-0.85

 Wellington

-0.83

erb

-0.82

Grey

-0.81

 Barg

-0.81

unic

-0.81

 Doodle

-0.81

POSITIVE LOGITS

 sidx

0.94

 WATCHED

0.94

 evidenced

0.91

 intended

0.88

actionDate

0.87

 liking

0.87

ãĤ¡

0.86

maxwell

0.86

ription

0.84

 indicated

0.83

Activations Density 1.067%

legal and policy-related terms

No Comments

No Known Activations