Update README.md
Browse files
README.md
CHANGED
@@ -4,7 +4,8 @@ language:
|
|
4 |
- en
|
5 |
---
|
6 |
|
7 |
-
This is the
|
|
|
8 |
|
9 |
The model was trained on the residual stream in the 10th layer of instruction-tuned [Gemma 2 27B](https://huggingface.co/google/gemma-2-27b-it), using a proprietary synthetic dataset with psychopathology symptom labels. The model weight precision is bfloat16, and the hidden dimension size is 8 times that of the LLM residual stream.
|
10 |
|
|
|
4 |
- en
|
5 |
---
|
6 |
|
7 |
+
This is trained model parameters of the **S**entence-level, **S**upervised, **S**parse **A**uto**E**ncoder (S3AE) proposed in the paper ["Emergence of psychopathological computations in large language models"](https://arxiv.org/abs/2504.08016).
|
8 |
+
Codes with model architecture and use examples can be found in this [Github](https://github.com/syleeheal/Machine_Psychopathology).
|
9 |
|
10 |
The model was trained on the residual stream in the 10th layer of instruction-tuned [Gemma 2 27B](https://huggingface.co/google/gemma-2-27b-it), using a proprietary synthetic dataset with psychopathology symptom labels. The model weight precision is bfloat16, and the hidden dimension size is 8 times that of the LLM residual stream.
|
11 |
|