Subject

Mechanistic interpretability

4 open-access journal articles on mechanistic interpretability, published in 2026 in Life of Research. Every record is free to read and download, with a permanent link and a ready-made citation.

4 records

Journal article

Repair Without a Repairer: Five Mechanisms Called Self-Repair in Neural Networks, Why Much of the Measured Restoration Is Restored Scale, and What Would License the Claim That a Network Restores Its Own Performance

Pranay Mahendrakar 2026

"Self-repair" is used in at least three research communities that do not cite one another. In transformer interpretability it names the Hydra effect: when one component is ablated, later components shift their output and partly restore the logit. In neuromorphic engineering it names…

Cite Related research LOR-00104 · 7 views · 14 downloads

PDF411.6 KB

Journal article

Circuits Are Estimates, Not Mechanisms: A Recovered Subgraph Is One Draw From a Class Set by the Ablation, the Dataset and the Grain, the Results That Defend Circuits Hold at the Level of That Class, and What Ablation Evidence Licenses at Each Level

Pranay Mahendrakar 2026

A circuit in a language model is usually presented as the mechanism by which the model performs a task: a sparse subgraph, found by ablation or patching, that reproduces the behaviour when everything else is knocked out. A second body of work, mostly from 2024 to 2026, reports that the subgraph…

Cite Related research LOR-00098 · 9 views · 13 downloads

PDF395.2 KB

Journal article

A Control Knob Is Not a Concept: What a Working Steering Vector Licenses, Why Its Equivalence Class Is Set by the Readout That Scores It, and the Controls That Would Upgrade Control to Representation

Pranay Mahendrakar 2026

Adding a vector to a language model's residual stream and watching a behaviour change has become the field's most common argument that the model represents a concept along that vector. Refusal directions, persona vectors, truth directions and instruction vectors are all reported this way. A second…

Cite Related research LOR-00099 · 7 views · 4 downloads

PDF393 KB

Journal article

Dictionaries Without Ontologies: What a Sparse Autoencoder Latent Is Evidence For, Why Decodability, Use and Reproducibility Do Not Add Up to Canonicity, and the Identifiability Premise No Real-Model Result Has Checked

Pranay Mahendrakar 2026

Sparse autoencoders are now the default instrument for decomposing language model activations, and their latents are routinely reported as the model's features: units the network itself uses, which a wide enough dictionary has pulled out of superposition. This paper asks what a latent is evidence…

Cite Related research LOR-00096 · 7 views · 7 downloads

PDF405.3 KB

Cite

APA

BibTeX

Import into a reference manager: BibTeX · RIS (Zotero, Mendeley, EndNote)