← Back to KHAO

Anthropic · Claude ·

Final token "the" opens a noun phrase completing the "21 of the ___" construction

2 min read

Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.

◌ Single Source

A line graph for the plausibility rates of the plausible- and implausible-initialized NLAs.

These metaphors are charming.

Key facts

Summary

Natural language autoencoders are meant to take in an LLM's activation vector and describe in plain text what the model is thinking. The team show that Qwen2.5-7B NLAs have some robustness to irrelevant statements and prevailing sentiments in Claude's guesses. However, if an NLA is initialized with entirely implausible statements, it can nevertheless achieve nearly the same reconstruction accuracy as plausible-initialized NLAs while emitting 99.3% implausible statements. Produced as part of the MATS program in the summer 2026 cohort of team shard. "Plausible-initialized" NLAs are initialized normally using Claude's guesses. Slava Chalnev and a team at Anthropic (Fraser-Taliente et al. 2026) recently independently invented NLAs. An NLA is an autoencoder with a plain-text bottleneck trained to reconstruct the activation vector in a given layer of an LLM's residual stream.

Read full article at Alignment Forum →

#Anthropic #Claude