INDEX

Explanations

references to feature selection algorithms and their complexities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

raisemb

-0.59

坐

-0.53

'{@

-0.51

commutative

-0.49

 caul

-0.49

MAND

-0.48

bazel

-0.47

をめ

-0.46

Atsauces

-0.45

 Communic

-0.45

POSITIVE LOGITS

 method

0.90

 methode

0.83

 technique

0.83

 metode

0.80

 metod

0.76

 método

0.75

 metoda

0.74

 methods

0.74

method

0.71

 metodo

0.70

Activations Density 1.456%

references to feature selection algorithms and their complexities

No Comments

No Known Activations