INDEX

Explanations

structured elements and references related to programming or database queries

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

mathematical expression syntax

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

MessageOf

-0.63

RenderAtEndOf

-0.55

PerformLayout

-0.51

ScopeManager

-0.50

parsedMessage

-0.50

évaluateur

-0.44

帖最后由

-0.44

ArgumentParser

-0.43

المكان

-0.42

getColumnIndex

-0.42

POSITIVE LOGITS

 Biôgrafia

0.55

PhysRev

0.45

 EClass

0.42

ngdoc

0.40

 Comisión

0.39

Хьажоргаш

0.39

 vitt

0.39

Maße

0.38

DataAnnotations

0.38

TableAdapter

0.37

Activations Density 0.070%

structured elements and references related to programming or database queries

mathematical expression syntax

No Comments

No Known Activations