INDEX

Explanations

phrases related to medical conditions and treatments

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

following "a" that start an invention/product name

np_acts-logits-general · gemini-2.0-flash

determines definitions/categories

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 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

 ExecuteAsync

-0.65

 ModelExpression

-0.65

 tertentu

-0.62

IndentedString

-0.58

 nakalista

-0.57

 Biôgrafia

-0.56

pective

-0.56

SourceChecksum

-0.55

 بيها

-0.55

 متعلقه

-0.54

POSITIVE LOGITS

 onderdeel

0.80

 popular

0.73

 continuation

0.71

 ऐसा

0.69

 abbreviation

0.69

 type

0.68

 relatively

0.68

 outgrowth

0.67

 part

0.67

 term

0.66

Activations Density 0.490%

phrases related to medical conditions and treatments

following "a" that start an invention/product name

determines definitions/categories

No Comments

No Known Activations