INDEX

Explanations

political terms and discussions related to legislation and government actions

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

asso

-1.03

eeks

-0.96

older

-0.96

URL

-0.95

grave

-0.95

Dial

-0.92

someone

-0.90

Zip

-0.88

simple

-0.87

 Applicant

-0.85

POSITIVE LOGITS

quartered

0.95

ãĤ´ãĥ³

0.89

 pseudo

0.88

 coalition

0.87

 paramilitary

0.85

gling

0.85

omn

0.81

tir

0.80

iliary

0.79

hal

0.79

Activations Density 1.407%

political terms and discussions related to legislation and government actions

No Comments

No Known Activations