INDEX

Explanations

phrases related to physical movement and spatial orientation within a physical environment

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ortunate

-0.96

ilic

-0.88

catentry

-0.88

bringing

-0.86

undai

-0.80

²¾

-0.80

 ingred

-0.80

achev

-0.78

¿½

-0.78

İĭ

-0.78

POSITIVE LOGITS

 halls

1.03

 doors

0.85

 door

0.83

 corridors

0.82

 sidelines

0.79

 Dane

0.78

 hallway

0.77

 hall

0.74

 rooft

0.74

 darkened

0.74

Activations Density 7.321%

phrases related to physical movement and spatial orientation within a physical environment

No Comments

No Known Activations