INDEX

Explanations

specific entities or terms related to statistical tests and scientific terminology

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

apache commons math distributions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

httphttps

-0.76

دانشنامهٔ

-0.75

IntoConstraints

-0.71

Datuak

-0.68

ViewFeatures

-0.67

 مشين

-0.66

 كومونز

-0.65

expandindo

-0.64

 otomatig

-0.63

 kasarigan

-0.63

POSITIVE LOGITS

行政区划

0.39

kheim

0.35

 definitive

0.33

effectuer

0.33

Fib

0.33

 اف

0.33

abbix

0.32

InputElement

0.32

 indoss

0.31

 Ajoutez

0.30

Activations Density 0.031%

specific entities or terms related to statistical tests and scientific terminology

apache commons math distributions

No Comments

No Known Activations