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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7-RES-JB
    6. 9602
    Prev
    Next
    INDEX
    Explanations

    medical and healthcare professionals, including specific specialties like chiropractic, neurology, obstetrics, and veterinary medicine

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Orwell
    -0.75
     iPod
    -0.72
     WikiLeaks
    -0.70
     Snowden
    -0.68
    sung
    -0.65
     Territories
    -0.64
    ãĥĪ
    -0.63
    bucks
    -0.63
    ontent
    -0.63
    bley
    -0.62
    POSITIVE LOGITS
     practitioner
    1.23
     physician
    1.07
    opathic
    1.04
     physicians
    1.02
     prescribing
    1.01
     medicine
    1.00
    inical
    1.00
     practitioners
    0.98
    rolog
    0.97
     surgeon
    0.96
    Activations Density 0.105%

    No Known Activations