INDEX

Explanations

terms and concepts related to machine learning and statistical estimation methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

Chham

-0.45

StructEnd

-0.44

 utafitiHapana

-0.43

Eksterne

-0.40

 designations

-0.38

idiary

-0.36

Portály

-0.36

ause

-0.34

 scopes

-0.34

arrows

-0.33

POSITIVE LOGITS

 algorithms

0.73

 algorithm

0.72

 algorit

0.71

preduce

0.67

算法

0.67

SVM

0.67

gorit

0.66

 unsupervised

0.66

 Algorithm

0.66

 algoritmo

0.65

Activations Density 2.800%

terms and concepts related to machine learning and statistical estimation methods

No Comments

No Known Activations