INDEX

Explanations

technical terms and references associated with programming or coding structures

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

code declarations and functions

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

ViewImports

-0.79

 الحره

-0.57

 invokingState

-0.49

 calendriers

-0.49

PARATUS

-0.48

XtraReports

-0.47

Rüyada

-0.47

 كومونز

-0.46

 MyBatis

-0.45

XmlAccessorType

-0.45

POSITIVE LOGITS

IBAction

0.32

 onBind

0.31

 CURIAM

0.31

endwhile

0.30

 titulaire

0.30

 endwhile

0.30

исленность

0.29

اتور

0.29

 oeuvres

0.29

ませ

0.29

Activations Density 0.425%

technical terms and references associated with programming or coding structures

code declarations and functions

No Comments

No Known Activations