conftrace_

activation patching

29 papers

Explore in graph

Co-occurring keywords · papers mentioning both

mechanistic interpretability (13) large language model (7) circuit discovery (4) transformer model (3) attention head (3) language model (3) causal interpretability (2) causal tracing (2) multilingual language model (2) concept representation (2)

Papers

Mitigating Privacy Seesaw in Large Language Models: Augmented Privacy Neuron Editing via Activation Patching ACL 2024 Monotonic Representation of Numeric Attributes in Language Models ACL 2024 Towards Best Practices of Activation Patching in Language Models: Metrics and Methods ICLR 2024 Towards Automated Circuit Discovery for Mechanistic Interpretability NeurIPS 2023