INDEX

Explanations

terms related to energy efficiency and conservation

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 glim

-0.90

 haul

-0.87

 magically

-0.86

 swoop

-0.85

guy

-0.83

 nomine

-0.83

 tack

-0.83

 nodd

-0.82

 stuff

-0.79

 yell

-0.78

POSITIVE LOGITS

 Consequently

1.66

 Moreover

1.60

 Furthermore

1.57

 Accordingly

1.56

 Therefore

1.53

 Nevertheless

1.52

 Additionally

1.52

 Nonetheless

1.48

 Such

1.41

 Although

1.41

Activations Density 0.452%

terms related to energy efficiency and conservation

No Comments

No Known Activations