---
license: mit
---
Cached SAE acts stored in CSR format. Not especially optimized for others' use/fleshed out.

If you want to use them, do

```
import torch

csr_kwargs = torch.load('FEAT_IDX.pt')

# The matrices are stored in space-efficient formats that're incompatible with torch's sparse csr tensor.
# Convert them back before constructing the matrix.
csr_kwargs['crow_indices'] = csr_kwargs['crow_indices'].int()
csr_kwargs['col_indices'] = csr_kwargs['crow_indices'].int()
csr_kwargs['values'] = csr_kwargs['values'].float()/255

feat_acts = torch.sparse_csr_tensor(**csr_kwargs)
```