INDEX

Explanations

terms related to various genders, sexual orientations, lifestyles, and societal norms

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

 Monument

-0.39

roller

-0.37

 Palmer

-0.36

 Jarrett

-0.36

Haunted

-0.35

 valiant

-0.35

araoh

-0.35

 Porter

-0.34

 Doodle

-0.34

 Bowser

-0.34

POSITIVE LOGITS

specified

0.49

 substit

0.49

 sidx

0.49

 duplication

0.47

idth

0.43

appropriate

0.42

 spoilers

0.40

 practicable

0.40

 qualitative

0.39

 quantitative

0.39

Activations Density 12.078%

terms related to various genders, sexual orientations, lifestyles, and societal norms

No Comments

No Known Activations