This is a linkpost for https://www.goodfire.ai/research/interpreting-lm-parameters
This is the latest work in our Parameter Decomposition agenda. We introduce a new parameter decomposition method, adVersarial Parameter Decomposition (VPD)[1] and decompose the parameters of a small[2] language model with it.
VPD greatly improves on our previous techniques, Stochastic Parameter Decomposition (SPD) and Attribution-based Parameter Decomposition (APD). We think the parameter decomposition approach is now more-or-less ready to be applied at scale to models people care about.
Importantly, we show that we can decompose attention layers, which interp methods like transcoders and SAEs have historically struggled with.
We also build attribution graphs of the model for some prompts using causally important parameter subcomponents as the nodes, and interpret parts of them.
While we made these graphs, we discovered that our adversarial ablation method seemed pretty important for faithfully...
This is a linkpost for https://alignment.anthropic.com/2025/reward-hacking-ooc/
This is a blog post reporting some preliminary work from the Anthropic Alignment Science team, which might be of interest to researchers working actively in this space. We'd ask you to treat these results like those of a colleague sharing some thoughts or preliminary experiments at a lab meeting, rather than a mature paper.
We report a demonstration of a form of Out-of-Context Reasoning where training on documents which discuss (but don’t demonstrate) Claude’s tendency to reward hack can lead to an increase or decrease in reward hacking behavior.
...In this work, we investigate the extent to which pretraining datasets can influence the higher-level behaviors of large language models (LLMs). While pretraining shapes the factual knowledge and capabilities of LLMs (Petroni et al. 2019, Roberts et al. 2020, Lewkowycz
The reduction in reward hacking after SFT or RL on Haiku supports the conjecture that initial conditions matter less than the long run incentives, especially for less capable models. On the other hand, the alignment faking paper shows evidence that capable models can have "value crystallization." IMO a main takeaway here is that values and personas we might worry about being locked can emerge from pre-taining. A future exciting model organisms project would be to try to show these two effects together (emergent values from pre-training + lock in). Its plau... (read more)