INDEX

Explanations

questions in the text

oai_token-act-pair · gpt-3.5-turbo

rhetorical questions

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

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

 specific

-0.74

 critical

-0.69

 myster

-0.67

 clin

-0.67

 disciplines

-0.67

 mascul

-0.67

mination

-0.66

eni

-0.65

 satell

-0.65

 precise

-0.64

POSITIVE LOGITS

 Nope

1.51

 Well

1.47

Yep

1.35

Try

1.30

 Yeah

1.29

 Probably

1.27

 Consider

1.25

 Then

1.22

 Congratulations

1.22

 Maybe

1.21

Activations Density 0.096%

questions in the text

rhetorical questions

No Comments

No Known Activations