INDEX

Explanations

content or discussions related to software development and coding, especially focusing on specific programming languages and technical implementation details

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

accompan

-0.50

eded

-0.49

"/>

-0.49

 paran

-0.48

 thereto

-0.45

bro

-0.44

 carved

-0.44

 bureau

-0.44

police

-0.44

 carving

-0.43

POSITIVE LOGITS

 Logged

0.69

 partName

0.60

 Overall

0.57

roma

0.54

ibliography

0.54

erion

0.53

 Conclusion

0.52

 Paste

0.52

pour

0.52

braska

0.51

Activations Density 24.857%

content or discussions related to software development and coding, especially focusing on specific programming languages and technical implementation details

No Comments

No Known Activations