INDEX

Explanations

information related to practical advice on various topics like business, manufacturing, health, and lifestyle tips

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

 inaug

-0.57

 destined

-0.53

 cartel

-0.52

 dere

-0.52

 sovereign

-0.52

 herself

-0.52

 ratified

-0.52

 sacked

-0.51

 marching

-0.51

 alive

-0.51

POSITIVE LOGITS

Example

1.03

Learn

0.97

Additionally

0.94

Therefore

0.93

Conclusion

0.90

Different

0.89

Examples

0.88

Furthermore

0.87

Optional

0.86

Avoid

0.86

Activations Density 20.421%

information related to practical advice on various topics like business, manufacturing, health, and lifestyle tips

No Comments

No Known Activations