anchor
Findings
- IC-054Gemma 2 2B performance degrades substantially when routed through Gemma Scope SAEs, and SAE-based feature suppression causes broad cross-domain degradation rather than targeted knowledge removal [eval]
- IC-1518Domain finetuning of LLaMA 2 7B, LLaMA 2 13B, and GPT-2 XL on PubMed causes topic and style priors to shift dramatically, accounting for the majority of the probability change, while factual knowledge learning contributes only a small fraction [eval]
- IC-43256 LLMs from 19 families exhibit u-shaped scaling on hard questions and inverted-U scaling on easy questions, with the opposing trends explaining emergent ability stagnation [eval]
- IC-451Transformer block coupling of Jacobian singular vectors positively correlates with benchmark performance across 30+ LLMs, more strongly than parameter count, depth, or embedding dimension [eval]
- IC-452Transformer block coupling is absent at initialization and increases persistently throughout training in Pythia 12B and 6.9B, with layer-wise locality emerging [eval]
- IC-453Hidden representation trajectories in trained LLMs exhibit considerable linearity (mean LSS 4.25) compared to 6.54 at initialization, and linearity increases with training [eval]
- IC-468Llama-3.1-405B's last hidden layer embeddings of erroneous tokens contain a linearly detectable error signal that a simple logistic regression head can exploit to flag incorrect continuations [source]
- IC-472The degree of emergence metric derived from Pythia's internal structure positively correlates with benchmark performance across training epochs [eval]
- IC-592The log-likelihood layer in LLaMA-2-7B, LLaMA-2-7B-Chat, Vicuna-7B, and Mistral-7B-Instruct produces factually incorrect answers on TruthfulQA MC1 (817 samples) due to a misalignment between the output distribution and internal attention head representations, with LM-to-head-norm accuracy gaps of 24.23 to 40.68 points. [eval]
- IC-626Llama 7B retains 95% of its common sense reasoning performance when compressed to 2 GB using JLCM [eval]
- IC-945LLaMA-2, MPT, Falcon, Pythia, and BERT-base-uncased allocate disproportionate attention to initial tokens regardless of their semantic content [eval]