INDEX

Explanations

phrases related to political actions, legislation, and government representatives

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

lessly

-1.02

LER

-1.01

ler

-0.97

etts

-0.94

cellent

-0.92

 ..........

-0.92

hered

-0.92

kok

-0.92

hra

-0.91

igraph

-0.89

POSITIVE LOGITS

ities

1.13

 powerhouse

0.99

 prowess

0.98

 affairs

0.98

 administrations

0.96

 heights

0.96

 enqu

0.95

 councils

0.94

 ambitions

0.93

 inquiries

0.93

Activations Density 3.141%

phrases related to political actions, legislation, and government representatives

No Comments

No Known Activations