REVIEW 5 cited by
Mechanistic?
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
The rise of the term "mechanistic interpretability" has accompanied increasing interest in understanding neural models -- particularly language models. However, this jargon has also led to a fair amount of confusion. So, what does it mean to be "mechanistic"? We describe four uses of the term in interpretability research. The most narrow technical definition requires a claim of causality, while a broader technical definition allows for any exploration of a model's internals. However, the term also has a narrow cultural definition describing a cultural movement. To understand this semantic drift, we present a history of the NLP interpretability community and the formation of the separate, parallel "mechanistic" interpretability community. Finally, we discuss the broad cultural definition -- encompassing the entire field of interpretability -- and why the traditional NLP interpretability community has come to embrace it. We argue that the polysemy of "mechanistic" is the product of a critical divide within the interpretability community.
Forward citations
Cited by 5 Pith papers
-
Propositional Interpretability in Artificial Intelligence
Chalmers proposes propositional interpretability, interpreting AI in terms of beliefs, desires, and credences, and sets the challenge of thought logging all such attitudes over time.
-
Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks
An unsupervised method, EDDP, jointly learns encoding-decoding direction pairs for concepts in CNN latent spaces, recovering interpretable and influential concepts without labels, validated on synthetic and real data.
-
Unpacking Robustness in Inflectional Languages: Adversarial Evaluation and Mechanistic Insights
Circuits extracted from inflectionally varied Polish sentences are more robust to adversarial word attacks than circuits from syncretic or English variants, identifying layer-0 attention heads as inflection-specific.
-
Towards Unified Attribution in Explainable AI, Data-Centric AI, and Mechanistic Interpretability
A position paper unifying feature, data, and component attribution under three shared techniques, perturbation, gradient, and linear approximation, and proposing cross-attribution research directions.
-
Evaluating Explanations: An Explanatory Virtues Framework for Mechanistic Interpretability -- The Strange Science Part I.ii
The paper introduces an Explanatory Virtues Framework and argues, via a qualitative rubric, that Compact Proofs are the most promising method for mechanistic interpretability.
Discussion (0). Continue with ORCID to comment.