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. 0-RES-JB
    6. 8574
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Hamilton" with variations in spelling or contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Hamilton."

    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
    ======
    -0.86
    ====
    -0.82
    ========
    -0.73
     xp
    -0.72
     wipe
    -0.70
     Shy
    -0.69
     skins
    -0.68
     =================================
    -0.68
    cfg
    -0.68
     spawn
    -0.68
    POSITIVE LOGITS
     Hamilton
    4.02
    Hamilton
    3.43
     McMaster
    1.55
     Madison
    1.49
     Wellington
    1.39
    Madison
    1.28
     Vaughan
    1.27
     Chattanooga
    1.26
     Higgins
    1.22
     Windsor
    1.22
    Activations Density 0.017%

    No Known Activations