INDEX

Explanations

code-related classes and examples in programming languages

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

Followed by parentheses and "Test"

np_acts-logits-general · gemini-2.0-flash

unit testing code

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

SharedCtor

-0.41

orsese

-0.41

-0.40

 purpoſe

-0.40

GEBURTSDATUM

-0.40

ftagPool

-0.39

 <=",

-0.36

 indivíduo

-0.35

warrant

-0.35

LookAnd

-0.35

POSITIVE LOGITS

 snippetHide

0.77

HandlerContext

0.54

AndroidJUnit

0.54

 Experiments

0.50

 Experiment

0.49

Beispiel

0.48

ApplicationTests

0.48

jsdelivr

0.48

 Example

0.47

httphttps

0.46

Activations Density 0.250%

code-related classes and examples in programming languages

Followed by parentheses and "Test"

unit testing code

No Comments

No Known Activations