INDEX

Explanations

references to time periods (years or decades)

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

NB

-0.78

oops

-0.73

helm

-0.73

PAC

-0.72

haps

-0.71

perse

-0.71

sonian

-0.70

ubi

-0.70

onda

-0.68

wo

-0.67

POSITIVE LOGITS

 number

1.46

 percentage

1.43

 ratio

1.42

 average

1.42

 amount

1.33

 rate

1.30

 incidence

1.27

 proportion

1.24

 economy

1.23

 median

1.21

Activations Density 0.319%

references to time periods (years or decades)

No Comments

No Known Activations