INDEX

Explanations

legal and court case-related terms and phrases

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

cia

-1.01

asin

-0.99

ptoms

-0.96

bet

-0.95

phia

-0.95

hin

-0.91

 listens

-0.91

ortment

-0.90

orthy

-0.88

icrobial

-0.87

POSITIVE LOGITS

 ACLU

0.92

 Bolivia

0.89

 Scalia

0.89

gins

0.88

 Heller

0.88

 legalizing

0.86

Ply

0.85

 Wyoming

0.82

EFF

0.82

 FIRE

0.80

Activations Density 0.240%

legal and court case-related terms and phrases

No Comments

No Known Activations