INDEX

Explanations

keywords and terms related to programming and technical documentation

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

Variant:Texture:<start_of_turn> user

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

 helmet

-0.34

Violation

-0.33

 tatlı

-0.33

NamedQuery

-0.32

 kaynağından

-0.32

 링크

-0.31

Trọng

-0.31

ัย

-0.31

maf

-0.31

 decorado

-0.31

POSITIVE LOGITS

 surla

0.82

Autoritní

0.68

 للمعارف

0.68

 autorytatywna

0.67

HasAnnotation

0.60

 Normdatei

0.57

 beginnetje

0.57

MigrationBuilder

0.56

NameInMap

0.55

Diweddarwch

0.55

Activations Density 0.000%

keywords and terms related to programming and technical documentation

Variant:Texture:<start_of_turn> user

No Comments

No Known Activations