INDEX

Explanations

terms related to evidence and its validation in contexts like studies or discussions of rights and processes

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

consequence or conclusion

np_acts-logits-general · gemini-2.0-flash

confirmation of quantity

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.30.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 einerseits

-0.60

and

-0.56

 namelijk

-0.54

 either

-0.51

 nämlich

-0.50

either

-0.47

 nemlig

-0.43

ListItemIcon

-0.41

 entweder

-0.41

الإنجليزية

-0.41

POSITIVE LOGITS

 consiguiente

0.73

それに

0.70

 therefrom

0.68

 sebagainya

0.68

 therefor

0.68

何より

0.66

 consequently

0.65

 importantly

0.64

 thereunder

0.64

 accordingly

0.63

Activations Density 1.501%

terms related to evidence and its validation in contexts like studies or discussions of rights and processes

consequence or conclusion

confirmation of quantity

No Known Activations

terms related to evidence and its validation in contexts like studies or discussions of rights and processes

consequence or conclusion

confirmation of quantity

No Known Activations