INDEX

Explanations

programming-related keywords, specifically those related to code structure and library usage

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

#include statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

transQ

-0.54

ngrx

-0.52

 betweenstory

-0.48

 ModelExpression

-0.47

TagMode

-0.45

featureID

-0.42

Fordítás

-0.41

nloa

-0.39

EndGlobalSection

-0.38

 resourceCulture

-0.38

POSITIVE LOGITS

 يتيمه

0.68

 للمعارف

0.63

 kasarigan

0.62

MemoryWarning

0.55

 Waray

0.50

ODB

0.48

 Collection

0.48

 تعدى

0.47

SequentialGroup

0.47

getCollection

0.47

Activations Density 0.000%

programming-related keywords, specifically those related to code structure and library usage

#include statements

No Comments

No Known Activations