Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
OpenBookQA
anchor
Findings
IC-054
Gemma 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-131
GPT-4 Turbo, GPT-3.5 Turbo, Llama3-8B, Qwen-7B, and iFlytekSpark-13B over-rely on the strong reminder 'the answer is' in prompts as a shortcut, with accuracy dropping sharply when the cue is a random answer rather than the ground truth
[eval]
IC-1499
Self-rationalization quality and task accuracy scale with model size across GPT-3, FLAN-T5, and LLaMA on five QA datasets
[eval]
IC-401
Ablating safety attention heads minimally degrades helpfulness on zero-shot tasks and also impairs course-correction capability in Llama-2-7b-chat
[eval]