INDEX

Explanations

mathematical notation and symbols related to functions and dimensional analysis

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

Mathematical notation/symbols

np_acts-logits-general · gemini-2.0-flash

mathematical dimension and rank

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 resourceCulture

-0.45

idados

-0.42

 Feeling

-0.40

 refresher

-0.39

 feeling

-0.39

 vittoria

-0.38

Feeling

-0.37

onda

-0.36

?>

-0.36

pā

-0.36

POSITIVE LOGITS

 Chwiliwch

0.83

enumi

0.83

 AssemblyProduct

0.73

 GenerationType

0.72

findpost

0.72

daß

0.71

 rank

0.71

 initComponents

0.70

__*/

0.70

исленность

0.70

Activations Density 2.571%

mathematical notation and symbols related to functions and dimensional analysis

Mathematical notation/symbols

mathematical dimension and rank

No Comments

No Known Activations