Magnitude of Vectors on chart not taking into account number of vectors?

[zrichz]

Hi - as far as I can tell with the code, there needs to be a division at the end of this code snippet to take into account the number of vectors used for the embedding, to get the average magnitude across all vectors:

def get_vector_data_magnitude(data: dict[int, dict[int, Tensor]], step: int) -> float: value = 0 for n in data[step]: value += pow(n, 2) value = math.sqrt(value) ##<------needs a divisor here? return value

as current this is just squaring every data point and then sqrt the result

[Zyin055]

So something like this?

def get_vector_data_magnitude(data: dict[int, dict[int, Tensor]], step: int) -> float:
    value = 0
    for n in data[step]:
        value += pow(n, 2)
    vectors_per_token = int(len(data[step]) / DIMS_PER_VECTOR) #ie: 1, 3, 10, etc
    value = math.sqrt(value) / vectors_per_token
    return value

[zrichz]

Yes I believe so. I was trying to write this change but didn't realise you had to explicitly define the vectors per token again. I'm happy to test this tonight and let you know

[zrichz]

to update, I have tested your code change on a 3-vector TI, and all looks great - the new Average Vector magnitude (top image) reports as 4.5.. and not 3x that (13.7..), and the average vector strength is (rightly) unaffected.