INDEX

Explanations

terms related to feature selection and classification algorithms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 NSCoder

-0.81

 للاسماء

-0.76

ArgsConstructor

-0.63

 Paused

-0.61

preventDefault

-0.60

IBarButtonItem

-0.58

 Raceway

-0.57

principalColumn

-0.57

raza

-0.56

 bitten

-0.56

POSITIVE LOGITS

 sklearn

0.53

 Sjö

0.50

cop

0.44

export

0.44

Portail

0.43

 processes

0.42

Viitteet

0.42

 extracts

0.42

agi

0.42

getOut

0.42

Activations Density 1.349%

terms related to feature selection and classification algorithms

No Comments

No Known Activations