`task.py` fails due to changed defaults in PyTorch 2.6

[Tauheed-Elahee]

I'm running this with updated python libraries. PyTorch 2.6 updated it's default value from True to False.

Traceback (most recent call last):
  File "/data/Reference_Papers/MultiDimensionalFeatures/intervention/circle_probe_interventions.py", line 184, in <module>
    acts, pca_obj = get_acts_pca(
                    ^^^^^^^^^^^^^
  File "/data/Reference_Papers/MultiDimensionalFeatures/intervention/task.py", line 238, in get_acts_pca
    return torch.load(act_file_name), pkl.load(open(pca_pkl_file_name, "rb"))
           ^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/miniconda/lib/python3.12/site-packages/torch/serialization.py", line 1548, in load
    raise pickle.UnpicklingError(_get_wo_message(str(e))) from None
_pickle.UnpicklingError: Weights only load failed. This file can still be loaded, to do so you have two options, do those steps only if you trust the source of the checkpoint.
        (1) In PyTorch 2.6, we changed the default value of the `weights_only` argument in `torch.load` from `False` to `True`. Re-running `torch.load` with `weights_only` set to `False` will likely succeed, but it can result in arbitrary code execution. Do it only if you got the file from a trusted source.
        (2) Alternatively, to load with `weights_only=True` please check the recommended steps in the following error message.
        WeightsUnpickler error: Unsupported global: GLOBAL numpy.core.multiarray._reconstruct was not an allowed global by default. Please use `torch.serialization.add_safe_globals([numpy.core.multiarray._reconstruct])` or the `torch.serialization.safe_globals([numpy.core.multiarray._reconstruct])` context manager to allowlist this global if you trust this class/function.

Check the documentation of torch.load to learn more about types accepted by default with weights_only https://pytorch.org/docs/stable/generated/torch.load.html.