INDEX

Explanations

phrases and terms related to political and legal concepts, particularly focusing on constitutional amendments and government issues

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bos

-0.95

tics

-0.84

flies

-0.81

ETS

-0.81

cks

-0.76

ded

-0.75

enne

-0.74

dump

-0.73

feed

-0.73

atable

-0.72

POSITIVE LOGITS

 Amendment

1.30

 Century

1.00

 Estate

1.00

 Circuit

0.99

 Edition

0.95

 Avenue

0.95

 Anniversary

0.95

 Presidency

0.93

 Month

0.93

Day

0.92

Activations Density 4.054%

phrases and terms related to political and legal concepts, particularly focusing on constitutional amendments and government issues

No Comments

No Known Activations