INDEX

Explanations

product specifications and features related to electronics, particularly focusing on model names and technical components

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

radio aux mode

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 مشين

-0.52

 intptr

-0.52

 CreateTagHelper

-0.51

 linkovi

-0.50

 otomatig

-0.50

 purpoſe

-0.49

 Houſe

-0.48

 myſelf

-0.46

geen

-0.45

 الرياضيه

-0.45

POSITIVE LOGITS

findpost

0.43

ReusableCell

0.43

wapV

0.41

ThroughAttribute

0.41

 getY

0.36

 NDEBUG

0.35

usammen

0.35

 setCurrent

0.35

 moviliz

0.35

舺

0.34

Activations Density 0.076%

product specifications and features related to electronics, particularly focusing on model names and technical components

radio aux mode

No Comments

No Known Activations