INDEX

Explanations

code elements related to the Boost library and template programming in C++

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

Code-related syntax or definitions

np_acts-logits-general · gemini-2.0-flash

protocol buffer messages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 Jurí

-0.46

 Picchu

-0.42

 سكانية

-0.39

rawDesc

-0.37

cheiben

-0.37

AddTagHelper

-0.37

Gön

-0.36

 validamos

-0.36

tión

-0.35

heça

-0.35

POSITIVE LOGITS

RegressionTest

0.71

-------------</

0.52

 Италијани

0.51

nonatomic

0.46

onedDateTime

0.45

AccessorTable

0.45

GeneratedMessage

0.45

ContentAlignment

0.44

 opérés

0.43

UnusedPrivate

0.43

Activations Density 0.849%

code elements related to the Boost library and template programming in C++

Code-related syntax or definitions

protocol buffer messages

No Comments

No Known Activations