INDEX

Explanations

references to nuts or nut-related terms

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

interstitial

-1.05

 payable

-0.82

utenberg

-0.79

 paycheck

-0.77

egal

-0.75

 Warsaw

-0.73

SPONSORED

-0.72

oping

-0.71

iter

-0.70

naire

-0.70

POSITIVE LOGITS

rient

1.65

ritional

1.53

rients

1.51

meg

1.40

tall

1.29

rition

1.28

ty

1.22

ting

1.20

te

1.20

ts

1.19

Activations Density 3.024%

references to nuts or nut-related terms

No Comments

No Known Activations