INDEX

Explanations

elements related to feature extraction and performance evaluation in machine learning

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

Feature extraction with CNNs

np_acts-logits-general · gemini-2.0-flash

feature information relevant

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 незавершена

-0.63

findpost

-0.57

Rhestr

-0.56

Personensuche

-0.56

 <>",

-0.55

MIDDLEWARE

-0.55

 diversion

-0.53

GraphicsUnit

-0.53

webElementXpaths

-0.53

 Pender

-0.52

POSITIVE LOGITS

 computationally

0.68

 heur

0.66

Cheap

0.58

 coarse

0.57

 computa

0.55

 fine

0.55

 explicit

0.54

 explicitly

0.54

 priori

0.53

 efficiently

0.53

Activations Density 1.663%

elements related to feature extraction and performance evaluation in machine learning

Feature extraction with CNNs

feature information relevant

No Comments

No Known Activations