INDEX

Explanations

equalities and assignments in programming code

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

Equals sign followed by "new"

np_acts-logits-general · gemini-2.0-flash

that new

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

revet

-0.56

:✨

-0.55

hynch

-0.55

Javadoc

-0.55

Datuak

-0.54

 RelativeLayout

-0.53

bibfnamefont

-0.52

ailleurs

-0.52

beek

-0.51

 inol

-0.51

POSITIVE LOGITS

new

2.39

new

2.12

 nuevas

1.56

 nuevos

1.55

 neuen

1.49

 nuovi

1.48

 neue

1.47

 nieuwe

1.46

 nuove

1.42

 новый

1.41

Activations Density 0.127%

equalities and assignments in programming code

Equals sign followed by "new"

that new

No Comments

No Known Activations