INDEX

Explanations

JavaScript function definitions and related syntax

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

angular.js patterns and keywords

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

GEBURTSDATUM

-0.55

 gyhoeddwyd

-0.55

 Italijani

-0.53

 extérieurs

-0.49

 تعدى

-0.48

UrlResolution

-0.47

 nødvendig

-0.47

 beſt

-0.47

Personensuche

-0.47

 AssemblyCulture

-0.46

POSITIVE LOGITS

istoitu

0.44

 endwhile

0.39

MotionEvent

0.37

_.

0.36

 kaynağından

0.36

AutoScale

0.36

MARY

0.36

ResponseWriter

0.35

REA

0.35

lides

0.35

Activations Density 0.009%

JavaScript function definitions and related syntax

angular.js patterns and keywords

No Comments

No Known Activations