INDEX

Explanations

terms related to algorithms used for feature selection and data processing methodologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 NSCoder

-0.63

verwijspagina

-0.57

MockMvc

-0.57

Parcelize

-0.57

Manifest

-0.53

CastException

-0.52

)("

-0.51

TestingModule

-0.51

JsonFormat

-0.51

 Manifest

-0.50

POSITIVE LOGITS

 algorithm

1.50

 algorithms

1.41

 algorit

1.31

 algoritmo

1.29

 Algorithm

1.16

algorithm

1.08

 Algorithms

1.07

算法

1.04

Algorithm

1.04

 approach

0.99

Activations Density 1.479%

terms related to algorithms used for feature selection and data processing methodologies

No Comments

No Known Activations