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. 1-RES-JB
    6. 11058
    Prev
    Next
    INDEX
    Explanations

    mentions of aristocracy and specific names like 'Cahill'

    oai_token-act-pair · gpt-3.5-turbo

    references to social classes and specific individuals or families associated with aristocracy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sites
    -0.80
    Fuel
    -0.73
    nir
    -0.69
    TED
    -0.68
     Mandela
    -0.66
    NING
    -0.66
     Gins
    -0.64
     Electronics
    -0.63
    à¼
    -0.62
     Toys
    -0.62
    POSITIVE LOGITS
    ocrat
    1.06
    ocrats
    1.04
     arist
    0.86
     nobility
    0.83
    class
    0.78
     Arist
    0.78
    ublic
    0.77
    ourgeois
    0.77
    odies
    0.77
    ocratic
    0.76
    Activations Density 0.033%

    No Known Activations