INDEX

Explanations

programming and software development-related terminology, particularly within various frameworks and libraries

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

Code, dates, or statistics

np_acts-logits-general · gemini-2.0-flash

datetime, status, and code snippets

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

 мәкал

-0.72

endphp

-0.65

 nahilalakip

-0.65

aarrggbb

-0.64

 MainAxisSize

-0.63

 ſehr

-0.62

 numberWith

-0.62

 vPvB

-0.62

ſchaft

-0.61

POSITIVE LOGITS

SpringBootTest

0.39

InstrumentedTest

0.36

 error

0.31

 cavalli

0.30

 podamos

0.29

can

0.28

 виправивши

0.28

cookieParser

0.28

 vergüenza

0.28

 relatively

0.28

Activations Density 0.104%

programming and software development-related terminology, particularly within various frameworks and libraries

Code, dates, or statistics

datetime, status, and code snippets

No Comments

No Known Activations