INDEX

Explanations

technical terms related to scientific experimentation and analysis

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

followed by prepositions

np_acts-logits-general · gemini-2.0-flash

defined or configured

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 Verhältnisse

-0.38

 Erhöhung

-0.35

<h1>

-0.34

 Verhält

-0.34

 mít

-0.33

 Empfindung

-0.32

 maternidade

-0.32

 Zustimmung

-0.32

 Untersuchung

-0.31

LEGGI

-0.31

POSITIVE LOGITS

 kasarigan

0.86

 NSCoder

0.83

 المعيارى

0.81

 GenerationType

0.80

findpost

0.79

migrationBuilder

0.76

SourceChecksum

0.75

 HasFactory

0.74

 CreateTagHelper

0.73

ViewImports

0.72

Activations Density 0.938%

technical terms related to scientific experimentation and analysis

followed by prepositions

defined or configured

No Comments

No Known Activations