INDEX

Explanations

identifiers and attributes related to user interface elements in programming code

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

android id="@+id/"

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

shared

-0.37

 shared

-0.34

وبر

-0.34

coarse

-0.32

 أكتوبر

-0.32

質

-0.31

 taking

-0.31

course

-0.30

 coarse

-0.30

 Reine

-0.29

POSITIVE LOGITS

featureID

0.99

id

0.84

id

0.82

Id

0.82

ID

0.78

ViewById

0.75

Id

0.73

 setId

0.73

 getId

0.73

getId

0.71

Activations Density 0.002%

identifiers and attributes related to user interface elements in programming code

android id="@+id/"

No Comments

No Known Activations