INDEX

Explanations

specific geographic locations or areas mentioned in a technical or geographical context

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

vous

-1.12

lio

-0.88

inn

-0.88

icial

-0.80

enstein

-0.79

aldi

-0.79

estamp

-0.78

artz

-0.74

ging

-0.74

essed

-0.73

POSITIVE LOGITS

 area

0.91

 areas

0.83

rug

0.79

 surrounding

0.77

 adjacent

0.77

area

0.76

 bounded

0.75

 malls

0.75

 adjoining

0.74

 frequ

0.73

Activations Density 9.735%

specific geographic locations or areas mentioned in a technical or geographical context

No Comments

No Known Activations