chrisjcundy commited on
Commit
08942e4
·
verified ·
1 Parent(s): 4243ca7

docs: point the code link at AlignmentResearch/fibs-probes (paper renamed to Telling FIBS)

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -23,7 +23,7 @@ base_model:
23
  Trained activation probes in four architectures (linear, MLP, EFC (early-fusion covariance) and axial)
24
  for nine open-weight models. Each probe reads a model's residual-stream activations at six decoder
25
  layers and returns one score per transcript. Load them with the `probe-inference` package
26
- ([AlignmentResearch/caught-in-the-act-probes](https://github.com/AlignmentResearch/caught-in-the-act-probes)):
27
 
28
  ```python
29
  from probe_inference import load_probe_from_hub
 
23
  Trained activation probes in four architectures (linear, MLP, EFC (early-fusion covariance) and axial)
24
  for nine open-weight models. Each probe reads a model's residual-stream activations at six decoder
25
  layers and returns one score per transcript. Load them with the `probe-inference` package
26
+ ([AlignmentResearch/fibs-probes](https://github.com/AlignmentResearch/fibs-probes)):
27
 
28
  ```python
29
  from probe_inference import load_probe_from_hub