INDEX

Explanations

medical terms related to diagnostics and treatments

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Fiscal

-0.51

nai

-0.49

 âĢº

-0.48

 Pitch

-0.47

 HuffPost

-0.47

olls

-0.47

 Thomson

-0.45

 Comedy

-0.45

 Animals

-0.45

 Previous

-0.45

POSITIVE LOGITS

 destro

0.61

 cryst

0.60

'."

0.59

.'"

0.59

etheless

0.58

 payoff

0.57

endif

0.56

 endif

0.55

inguishable

0.54

 nonetheless

0.53

Activations Density 4.119%

medical terms related to diagnostics and treatments

No Comments

No Known Activations