INDEX

Explanations

technical terms and parameters related to programming and software development

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

propensity score matching

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

IsContent

-0.58

 onCancelled

-0.53

RegressionTest

-0.52

__*/

-0.49

はじめに

-0.49

($__

-0.47

ConstraintMaker

-0.47

üyada

-0.47

 esternos

-0.45

 springfox

-0.45

POSITIVE LOGITS

 propOrder

0.39

Autowired

0.38

ríamos

0.36

 soggetto

0.36

 ModelExpression

0.35

 inmediata

0.35

čenie

0.35

ntö

0.35

 vierge

0.34

 dumne

0.34

Activations Density 0.000%

technical terms and parameters related to programming and software development

propensity score matching

No Comments

No Known Activations