INDEX

Explanations

elements related to mathematical expressions and structures, specifically involving linear algebra and polynomial relations

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

Mathematical expressions with indexed variables

np_acts-logits-general · gemini-2.0-flash

ellipsis in formulas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

aarrggbb

-0.53

www

-0.45

 enkelt

-0.43

www

-0.42

strato

-0.42

WALL

-0.42

 walls

-0.41

SuppressMessage

-0.41

wall

-0.40

----------------

-0.40

POSITIVE LOGITS

 يتيمه

0.72

 Wikidata

0.72

 Spree

0.72

CloseOperation

0.71

Tikang

0.71

yntaxException

0.70

sizeCache

0.70

 NSCoder

0.69

Personendaten

0.68

 CiNii

0.67

Activations Density 0.208%

elements related to mathematical expressions and structures, specifically involving linear algebra and polynomial relations

Mathematical expressions with indexed variables

ellipsis in formulas

No Comments

No Known Activations