Merge pull request #163 from EleutherAI:SrGonao/issue143

Update readme

Author: SrGonao

README.md

@@ -16,15 +16,15 @@ Install this library as a local editable installation. Run the following command
 
 To run the default pipeline from the command line, use the following command:
 
-`python -m delphi EleutherAI/pythia-160m EleutherAI/Pythia-160m-SST-k32-32k --n_tokens 10_000_000 --max_latents 100 --hookpoints layers.5 --scorers detection --filter_bos --name llama-3-8B`
+`python -m delphi EleutherAI/pythia-160m EleutherAI/Pythia-160m-SST-k32-32k --n_tokens 10_000_000 --max_latents 100 --hookpoints layers.5.mlp --scorers detection --filter_bos --name llama-3-8B`
 
 This command will:
 1. Cache activations for the first 10 million tokens of the default dataset, `EleutherAI/SmolLM2-135M-10B`.
 2. Generate explanations for the first 100 features of layer 5 using the default explainer model, `hugging-quants/Meta-Llama-3.1-70B-Instruct-AWQ-INT4`.
 3. Score the explanations using the detection scorer.
 4. Log summary metrics including per-scorer F1 scores and confusion matrices, and produce histograms of the scorer classification accuracies.
 
-The pipeline is highly configurable and can also be called programmatically (see the [end-to-end test](https://github.com/EleutherAI/delphi/blob/main/delphi/tests/e2e.py) for an example).
+The pipeline is highly configurable and can also be called programmatically (see the [end-to-end test](https://github.com/EleutherAI/delphi/blob/main/tests/e2e.py) for an example).
 
 To use experimental features, create a custom pipeline. You can take inspiration from the main pipeline in [delphi.\_\_main\_\_](https://github.com/EleutherAI/delphi/blob/main/delphi/__main__.py).