INDEX

Explanations

specific mathematical and technical terms related to geometry and graphics rendering

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

object properties and coordinates

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

endpush

-0.41

DockStyle

-0.40

RegistryLite

-0.38

BackPressed

-0.35

providedIn

-0.34

帖最后由

-0.33

SerializedName

-0.33

ThroughAttribute

-0.31

 незавершена

-0.31

MessageTagHelper

-0.31

POSITIVE LOGITS

 Keuangan

0.56

 cabina

0.56

 Confira

0.53

Географиясе

0.52

 zwiſchen

0.52

 Extent

0.51

 tartalo

0.50

astéroïdes

0.50

terung

0.50

 interiores

0.50

Activations Density 0.188%

specific mathematical and technical terms related to geometry and graphics rendering

object properties and coordinates

No Comments

No Known Activations