Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 9866
    Prev
    Next
    INDEX
    Explanations

    references to medical professionals, particularly physicians

    oai_token-act-pair · gpt-3.5-turbo

    references to physicians and medical practitioners

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eworld
    -0.79
    flag
    -0.75
    yrinth
    -0.71
     Orwell
    -0.71
    urat
    -0.69
     Territories
    -0.69
    nings
    -0.69
    eat
    -0.68
    footed
    -0.68
    runners
    -0.68
    POSITIVE LOGITS
     physician
    1.13
     practitioner
    1.04
     physicians
    0.98
     doctor
    0.94
     prescribing
    0.88
     psychiatrist
    0.88
     prescriptions
    0.85
     examiner
    0.85
     care
    0.85
     surgeon
    0.83
    Activations Density 0.015%

    No Known Activations