INDEX

Explanations

punctuation

oai_token-act-pair · gpt-3.5-turbo

punctuation marks that end sentences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 imperson

-0.74

 elevated

-0.68

 treasury

-0.67

 boarded

-0.66

 dime

-0.65

eteen

-0.64

pul

-0.64

 plunge

-0.63

 marching

-0.63

vil

-0.63

POSITIVE LOGITS

 Lastly

1.64

 Finally

1.42

Lastly

1.25

 Anyway

1.21

Finally

1.18

 Nevertheless

1.15

 Furthermore

1.13

 ********************************

1.13

 Nonetheless

1.13

 Alternatively

1.10

Activations Density 0.584%

punctuation

punctuation marks that end sentences

No Comments

No Known Activations