INDEX

Explanations

dates written in the format of month followed by year

oai_token-act-pair · gpt-3.5-turbo

end punctuation in the text

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 purse

-0.80

 pudding

-0.77

 fishes

-0.74

 everywhere

-0.73

 jersey

-0.71

 rall

-0.71

 hats

-0.71

 naughty

-0.67

 elusive

-0.67

 disemb

-0.67

POSITIVE LOGITS

 However

1.03

 Since

1.01

 That

1.01

 Afterwards

1.00

 Additionally

0.93

 Needless

0.93

 Then

0.93

 During

0.93

 Previously

0.91

 According

0.91

Activations Density 0.547%

dates written in the format of month followed by year

end punctuation in the text

No Comments

No Known Activations