INDEX

Explanations

terms and phrases related to statistical models and estimators, indicating discussions of methodologies in data analysis and evaluation

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

Code-related tokens and special characters

np_acts-logits-general · gemini-2.0-flash

programming terms and scientific concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.28.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

 disambiguazione

-0.44

DeleteMapping

-0.44

FieldDescriptor

-0.42

bootstrapcdn

-0.41

ervis

-0.41

+#+

-0.40

AutoField

-0.40

 Vikipedi

-0.40

stdc

-0.40

fortawesome

-0.39

POSITIVE LOGITS

 للمعارف

0.55

 StatefulWidget

0.49

 gruesa

0.47

 agrícolas

0.47

formik

0.47

Искәрмәләр

0.45

itemBuilder

0.43

CreateModel

0.43

最快更新

0.43

 Gründer

0.42

Activations Density 2.093%

terms and phrases related to statistical models and estimators, indicating discussions of methodologies in data analysis and evaluation

Code-related tokens and special characters

programming terms and scientific concepts

No Comments

No Known Activations