INDEX

Explanations

technical terms associated with automation and production processes

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

Followed by "the", "installed", or "possible"

np_acts-logits-general · gemini-2.0-flash

offers the, were installed, also possible

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 exager

-0.53

 acum

-0.52

 inmig

-0.51

стр

-0.49

 imply

-0.48

 viceversa

-0.48

 personnal

-0.48

 Indeed

-0.47

Indeed

-0.45

 oxigen

-0.44

POSITIVE LOGITS

NUMX

0.81

GEBURTSDATUM

0.78

rungsseite

0.71

 استنادى

0.70

 Incidentally

0.69

+#+#

0.68

')")

0.67

^(@)

0.64

IonicModule

0.63

')";

0.63

Activations Density 0.427%

technical terms associated with automation and production processes

Followed by "the", "installed", or "possible"

offers the, were installed, also possible

No Comments

No Known Activations