INDEX

Explanations

references to the current object or instance in object-oriented programming

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

object oriented programming

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

 BoxFit

-0.39

.*")]

-0.38

}{@

-0.36

帖最后由

-0.36

LookAnd

-0.35

 мәкалә

-0.31

彦

-0.31

>>>>>>>

-0.30

[]=$

-0.30

دانشنامهٔ

-0.29

POSITIVE LOGITS

UserScript

0.56

tagHelperRunner

0.56

WindowConstants

0.56

 StatelessWidget

0.56

reportWebVitals

0.55

 mergeFrom

0.54

 Ashford

0.52

SharedCtor

0.51

ftagPool

0.50

FormTagHelper

0.49

Activations Density 0.013%

references to the current object or instance in object-oriented programming

object oriented programming

No Comments

No Known Activations