INDEX

Explanations

phrases that have unusual symbols or characters

oai_token-act-pair · gpt-3.5-turbo

unquantifiable statements and rhetorical questions

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

 phased

-0.78

 sucker

-0.71

 revers

-0.70

 submar

-0.70

 brid

-0.69

 Hero

-0.68

 frontline

-0.67

 tongue

-0.67

 consulate

-0.67

 reneg

-0.66

POSITIVE LOGITS

--------------------------------------------------------

1.55

Advertisements

1.41

======

1.37

CONCLUS

1.28

Conclusion

1.27

============

1.26

%%%%

1.26

------------------------------------------------

1.26

================

1.24

================================================================

1.22

Activations Density 0.186%

phrases that have unusual symbols or characters

unquantifiable statements and rhetorical questions

No Comments

No Known Activations