INDEX

Explanations

references to likelihood or possibility of a future event happening

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

anooga

-0.60

amps

-0.56

Tips

-0.56

Lear

-0.54

Textures

-0.52

Reporting

-0.52

 Canary

-0.52

anchester

-0.52

pointers

-0.51

tracks

-0.50

POSITIVE LOGITS

be

0.97

 become

0.79

 exclude

0.78

 absorb

0.77

 earn

0.77

 receive

0.77

 survive

0.76

 provoke

0.76

 satisfy

0.76

 attract

0.76

Activations Density 12.142%

references to likelihood or possibility of a future event happening

No Comments

No Known Activations