Naomi Saphra

Highlights: Naomi Saphra humorously comments on a space for scientific discourse, offering to share images of herself.

Worth reading: Shows her playful side and engagement with the scientific community.

Highlights: Naomi Saphra announces her upcoming faculty position at Boston University in 2026, excited about their work on language model interpretability.

Worth reading: Highlights her career move and research focus on LM interpretability.

Highlights: Announces a new preprint about phase transitions in language model training.

Worth reading: Relevant for researchers interested in training dynamics and phase transitions in LLMs.

Highlights: Announces new faculty position at Boston University focusing on LM interpretability.

Worth reading: Highlights career move and BU's research initiatives in interpretability.

Highlights: Naomi Saphra announces a new preprint on causal interpretability, emphasizing its coherent definition and testable predictions.

Worth reading: Highlights a key development in causal interpretability research.

Highlights: Bio/profile text indicating Saphra's role as a faculty member accepting PhD students and their stance on Grok.

Worth reading: Provides context on Saphra's professional status and interests.

Highlights: Announcement of starting as faculty at Boston University in 2026, focusing on LM interpretability.

Worth reading: Important career update and indication of research focus.

Highlights: Saphra humorously comments on a space for scientific discourse with self-deprecating tone.

Worth reading: Shows Saphra's playful side and engagement with scientific community.

Highlights: Saphra recommends a short, light read for a break during intense work.

Worth reading: Provides insight into Saphra's reading recommendations and work-life balance.

Highlights: Sarcastic comment about using images of oneself for scientific discourse.

Worth reading: Shows Saphra's humorous take on social media as a platform for science.

Highlights: Announces starting as faculty at Boston University in 2026.

Worth reading: Key career milestone for a prominent AI interpretability researcher.

Highlights: Announces a new preprint on causal interpretation, emphasizing its coherent definition and testable predictions.

Worth reading: Relevant for understanding recent advances in mechanistic interpretability of language models.

Highlights: Naomi Saphra humorously comments on a space for scientific discourse, starting with images of herself.

Worth reading: Shows her playful engagement with the scientific community on X.

Highlights: Naomi Saphra announces her upcoming faculty position at Boston University in 2026.

Worth reading: Highlights a major career milestone for a prominent AI researcher.

Highlights: Naomi Saphra humorously comments on using images of herself for scientific discourse.

Worth reading: Shows her playful engagement with the platform.

Highlights: Naomi Saphra announces her new faculty position at Boston University starting in 2026.

Worth reading: Key career milestone for a prominent AI researcher.

Highlights: Naomi Saphra humorously comments on using images of herself in a scientific discourse space.

Worth reading: Shows her playful engagement with online scientific communities.

Highlights: Announces her upcoming faculty position at Boston University in 2026.

Worth reading: Key career milestone for a prominent AI researcher.

Highlights: Naomi Saphra announces a new preprint on causal interpretability, emphasizing its coherent definition and testable predictions.

Worth reading: Highlights a new contribution to causal interpretability in AI, a key area for understanding model behavior.

Highlights: Naomi Saphra retweets a post about AI2 continuing to release open models despite industry changes.

Worth reading: Shows engagement with open model releases and industry dynamics.

Highlights: Describes her research focus on training dynamics and mechanistic interpretability in NLP models.

Worth reading: Summarizes her research interests.

Highlights: Sarcastic comment about scientific discourse, possibly related to AI.

Worth reading: Shows her critical perspective on AI discourse.

Highlights: Naomi Saphra announces a new preprint on causal interpretability, emphasizing its coherent definition and testable predictions.

Worth reading: Highlights a key advancement in AI interpretability research.

Highlights: Naomi Saphra shares that she has written up something, presumably a blog post or paper.

Worth reading: Indicates a new written work by the researcher.

Highlights: Announces a new preprint on causal interpretability, emphasizing its coherent definition and testable predictions.

Worth reading: Highlights a new contribution to AI interpretability research.

Highlights: Naomi Saphra announces a new preprint on causal interpretability, emphasizing its coherent definition and testable predictions.

Worth reading: Highlights ongoing work in AI interpretability, a key area for understanding and trusting AI models.

Highlights: Naomi Saphra humorously comments on using self-images to initiate scientific discourse.

Worth reading: Shows her playful engagement with the X platform.

Highlights: Naomi Saphra announces her new faculty position at Boston University starting in 2026.

Worth reading: Highlights her career move into academia.

Highlights: Sarcastic comment about scientific discourse on social media.

Worth reading: Reflects her critical perspective on online discussions.

Highlights: Describes her research focus on NLP model training and emergent behaviors.

Worth reading: Summarizes her research interests in interpretability.

Highlights: Announces a new preprint on causal interpretation, emphasizing its coherent definition and testable predictions.

Worth reading: Relevant for researchers interested in mechanistic interpretability and causal methods in AI.

Highlights: Indicates a write-up on a topic, with a link to further content.

Worth reading: May contain insights on AI training or interpretability, given Saphra's research focus.

Highlights: Describes research focus on NLP model training and emergence of mechanistic behaviors.

Worth reading: Provides context on Saphra's research interests in mechanistic interpretability and training dynamics.

Highlights: Naomi Saphra describes her research focus on understanding and improving NLP model training, specifically how structures and mechanistic behaviors emerge.

Worth reading: Provides insight into the author's research interests in mechanistic interpretability and training dynamics.

Highlights: Announces a new preprint on causal interpretability, emphasizing its coherent definition and testable predictions.

Worth reading: Highlights a new contribution to causal interpretability, a key area in AI safety and mechanistic understanding.

Highlights: Naomi Saphra shares an experience of receiving a desk reject after rebuttals due to a paper being submitted to arXiv less than 30 minutes late.

Worth reading: Illustrates the strictness of conference deadlines and the challenges in academic publishing.

Highlights: Sarcastic comment about using images of herself for scientific discourse.

Worth reading: Shows her humorous take on online scientific discussions.

Highlights: Announces a new preprint on causal interpretability, emphasizing its coherent definition and testable predictions.

Worth reading: Highlights a contribution to mechanistic interpretability, a key area in AI safety.

Highlights: Describes research focus on training dynamics and emergence of structures in NLP models.

Worth reading: Provides insight into the researcher's expertise in mechanistic interpretability and training.

Highlights: Naomi Saphra describes her research focus on understanding and improving NLP model training, particularly how structures and mechanistic behaviors emerge.

Worth reading: Provides insight into the research interests of a prominent NLP/ML researcher.

Highlights: Announces a new preprint on causal interpretability, emphasizing its coherent definition and testable predictions.

Worth reading: Highlights a new contribution to causal interpretability in ML.

Highlights: Naomi Saphra comments on a book about tuberculosis, noting its engaging start.

Worth reading: Shows a personal interest outside of AI/ML.

Highlights: Sarcastic comment about using images for scientific discourse.

Worth reading: Illustrates her humorous take on online discussions.

Highlights: Describes her research focus on NLP model training and emergent behaviors.

Worth reading: Summarizes her research interests.

Highlights: Sarcastic comment about using images of oneself for scientific discourse.

Worth reading: Shows her humorous take on online scientific communication.

Highlights: Announcement of starting as faculty at Boston University in 2026.

Worth reading: Highlights her career move into academia.

Highlights: Sarcastic comment about using images for scientific discourse.

Worth reading: Shows her humorous take on academic discussions.

Highlights: Announcement of new faculty position at Boston University.

Worth reading: Highlights her career move and impact on AI research.

Highlights: Describes her research focus on NLP model training and mechanistic behaviors.

Worth reading: Summarizes her research interests in AI interpretability.

Highlights: Sarcastic comment about using images in a scientific discourse space.

Worth reading: Shows her humorous take on academic communication.

Highlights: Announcement of joining Boston University as faculty in 2026.

Worth reading: Key career milestone for a prominent AI researcher.

Highlights: Describes her research focus on NLP model training and emergent behaviors.

Worth reading: Summarizes her research interests in mechanistic interpretability.

Highlights: Naomi Saphra comments on a book about tuberculosis, noting its engaging start.

Worth reading: Shows her casual reading interests.

Highlights: Announces a new preprint on causal interpretation, emphasizing its coherence and testability.

Worth reading: Highlights her research focus on causal interpretability.

Highlights: Announces a new preprint about phase transitions in language model training.

Worth reading: Relevant to understanding training dynamics of LLMs.

Highlights: Naomi Saphra announces starting as faculty at Boston University in 2026.

Worth reading: Shows career move and continued involvement in academia.

Highlights: Naomi Saphra announces she will join Boston University as faculty in 2026.

Worth reading: Shows career move of a prominent ML/NLP researcher.

Highlights: Naomi announces a new preprint on causal interpretation, emphasizing its coherent definition and testable predictions.

Worth reading: Highlights a new contribution to mechanistic interpretability, a key area in AI safety.

Highlights: Naomi Saphra announces she will join Boston University as faculty in 2026.

Worth reading: Shows a career milestone for a prominent AI researcher.

Highlights: Naomi references a write-up she authored, likely a blog post or paper.

Worth reading: Indicates a new piece of writing, possibly expanding on her research.

Highlights: Naomi Saphra describes her research on understanding and improving NLP model training, focusing on emergent structures and mechanistic behaviors.

Worth reading: Provides insight into her research focus on mechanistic interpretability in language models.

Highlights: Naomi describes her research focus on training dynamics and emergence of mechanistic behaviors in NLP models.

Worth reading: Provides context on her research agenda in mechanistic interpretability and training dynamics.