INDEX

Explanations

words related to medical discussions or terminology

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

Code, arrays, and XML elements

np_acts-logits-general · gemini-2.0-flash

numbers and programming keywords

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

 Вікіпе

-0.46

 Faculty

-0.40

Faculty

-0.38

 Racing

-0.38

 Facebook

-0.37

se

-0.36

derdag

-0.36

 Cement

-0.36

 Weller

-0.36

rfan

-0.36

POSITIVE LOGITS

 actionMode

0.50

windowFixed

0.46

 wireType

0.45

 ausgest

0.42

addCriterion

0.41

 saites

0.41

}{@

0.40

-------

0.40

"]}

0.40

]};

0.39

Activations Density 1.113%

words related to medical discussions or terminology

Code, arrays, and XML elements

numbers and programming keywords

No Comments

No Known Activations