INDEX

Explanations

terms related to classification processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/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.19.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

AndroidJUnit

-0.64

enterOuterAlt

-0.60

UnknownFieldSet

-0.55

canActivate

-0.53

 totalPrice

-0.52

 stepfather

-0.49

endola

-0.48

 Baillargeon

-0.47

 dési

-0.47

̍

-0.47

POSITIVE LOGITS

 classification

1.89

 categor

1.79

 classifications

1.78

 classifying

1.69

 categorization

1.68

 Classification

1.59

 classify

1.59

 categorize

1.58

classification

1.47

 Classi

1.46

Activations Density 0.945%

terms related to classification processes

No Comments

No Known Activations