INDEX

Explanations

quoted text

oai_token-act-pair · gpt-3.5-turbo

quotation marks indicating spoken dialogue

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 sacked

-0.74

 favour

-0.72

 arch

-0.71

 signalling

-0.67

 listed

-0.66

 smoot

-0.66

 moder

-0.62

 surname

-0.62

 finished

-0.62

 graz

-0.62

POSITIVE LOGITS

We

1.45

Our

1.39

Everybody

1.36

It

1.33

Nobody

1.33

Obviously

1.32

They

1.32

Absolutely

1.31

1.30

There

1.29

Activations Density 0.131%

quoted text

quotation marks indicating spoken dialogue

No Comments

No Known Activations