INDEX

Explanations

references to observable or reactive programming concepts

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

observable, computed, extenders

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 HasFactory

-0.70

webElementGuid

-0.65

AddTagHelper

-0.62

########.

-0.61

-0.58

 endwhile

-0.57

səhifə

-0.57

contentLoaded

-0.56

 pageContext

-0.56

ArgsConstructor

-0.55

POSITIVE LOGITS

 StringVar

0.38

createForm

0.33

MutableLiveData

0.33

FieldBuilder

0.32

project

0.32

sequelize

0.32

 BehaviorSubject

0.31

gonic

0.31

pipe

0.31

 projek

0.31

Activations Density 0.071%

references to observable or reactive programming concepts

observable, computed, extenders

No Comments

No Known Activations