© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 6510
    Prev
    Next
    INDEX
    Explanations

    references to the word "physician" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to physicians or related medical professionals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    trap
    -0.73
     flats
    -0.72
    Euro
    -0.69
     Stuff
    -0.68
    alling
    -0.65
     Remix
    -0.65
     Slam
    -0.65
     ruining
    -0.65
     Intercept
    -0.63
     boring
    -0.63
    POSITIVE LOGITS
     physician
    3.52
     physicians
    3.18
     Physicians
    2.32
     veterinarian
    2.04
     doctor
    1.97
     surgeon
    1.97
     clinicians
    1.97
     doctors
    1.97
     pediatric
    1.91
     veterin
    1.86
    Activations Density 0.024%

    No Known Activations