CLIPSetLastLayer maybe broken with the last update?

### Custom Node Testing

- [x] I have tried disabling custom nodes and the issue persists (see [how to disable custom nodes](https://docs.comfy.org/troubleshooting/custom-node-issues#step-1%3A-test-with-all-custom-nodes-disabled) if you need help)

### Expected Behavior

correct image generated

### Actual Behavior

corrupt image generated

### Steps to Reproduce

I'm using models from civitai and many recommends setting clip skip, 1 or 2 layers, these were working fine until I pulled the latest from github.

1) Add CLIPSetLastLayer to the workflow

### Debug Logs

```powershell
got prompt
model weight dtype torch.float16, manual cast: None
model_type EPS
Using xformers attention in VAE
Using xformers attention in VAE
VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16
Requested to load SDXLClipModel
loaded completely 9.5367431640625e+25 1560.802734375 True
CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cuda:0, dtype: torch.float16
Requested to load SDXLClipModel
Requested to load SDXL
loaded completely 20453.872158813476 4897.0483474731445 True
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 25/25 [00:07<00:00, 3.54it/s]
Requested to load AutoencoderKL
loaded completely 11841.819747924805 159.55708122253418 True
Prompt executed in 12.89 seconds
```

### Other

_No response_