INDEX

Explanations

phrases related to healthcare and medical terminology

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

before company names

np_acts-logits-general · gemini-2.0-flash

trusted business solutions and insights

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

aspectj

-0.63

(?)

-0.63

etc

-0.61

NameInMap

-0.59

 данного

-0.58

 jakieś

-0.58

(?)

-0.58

 oldukça

-0.57

ValueGenerated

-0.55

 Theoretical

-0.54

POSITIVE LOGITS

 everywhere

0.73

 uncompromising

0.70

 smarter

0.67

 trusted

0.67

 neceff

0.66

GEBURTSDATUM

0.66

 today

0.64

 jeito

0.64

 tomorrow

0.64

 ſtate

0.63

Activations Density 0.302%

phrases related to healthcare and medical terminology

before company names

trusted business solutions and insights

No Comments

No Known Activations