INDEX

Explanations

references to specific microcontroller brands and models

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

Microcontrollers or related components

np_acts-logits-general · gemini-2.0-flash

PIC and AVR microcontrollers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AndEndTag

-0.65

utilisons

-0.54

interopRequire

-0.49

 <>",

-0.48

obus

-0.47

 альбом

-0.46

 tornillos

-0.45

 iCloud

-0.44

 HDMI

-0.44

ApiModel

-0.44

POSITIVE LOGITS

avras

0.43

BeginContext

0.40

kegaard

0.37

хьтан

0.37

avr

0.36

 Flash

0.34

 flash

0.33

IntoConstraints

0.32

 sasaran

0.32

AVR

0.31

Activations Density 0.153%

references to specific microcontroller brands and models

Microcontrollers or related components

PIC and AVR microcontrollers

No Comments

No Known Activations