INDEX

Explanations

programming-related keywords and constructs in code snippets

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

layout manager set

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

 disambiguazione

-0.65

parsedMessage

-0.61

ExtendWith

-0.57

 bezeichneter

-0.54

الحياه

-0.52

 noDo

-0.51

AutoField

-0.49

 AssemblyCompany

-0.47

 betweenstory

-0.46

Portale

-0.45

POSITIVE LOGITS

IntoConstraints

0.74

LayoutManager

0.55

EndInit

0.49

layoutManager

0.46

setLayoutManager

0.44

ISupport

0.42

arrangement

0.40

Arrangement

0.39

 Arrange

0.38

 gerak

0.38

Activations Density 0.001%

programming-related keywords and constructs in code snippets

layout manager set

No Comments

No Known Activations