INDEX

Explanations

text sections that indicate significant breaks or transitions, such as paragraphs or line separators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

NUMX

-0.90

Hauptartikel

-0.86

 FetchType

-0.83

rawDesc

-0.83

msgSender

-0.80

PreferredItem

-0.78

MockBean

-0.78

出版年

-0.73

principalColumn

-0.70

')")

-0.70

POSITIVE LOGITS

↵↵

0.71

end

0.51

<eos>

0.51

oOo

0.50

↵

0.49

分割

0.49

---

0.48

End

0.46

END

0.46

 ----

0.46

Activations Density 0.555%

text sections that indicate significant breaks or transitions, such as paragraphs or line separators

No Comments

No Known Activations