INDEX

Explanations

names of geographical locations

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

erity

-0.94

minded

-0.85

 verbal

-0.84

hetically

-0.83

 acron

-0.83

matically

-0.83

 carbohyd

-0.82

ccording

-0.81

 hiring

-0.81

 courage

-0.81

POSITIVE LOGITS

 Peninsula

1.54

 Basin

1.46

 peninsula

1.35

 Fields

1.31

 Heights

1.25

 River

1.24

 Passage

1.23

 Gardens

1.22

 Islands

1.20

 Waters

1.18

Activations Density 1.580%

names of geographical locations

No Comments

No Known Activations