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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 30154
    Prev
    Next
    INDEX
    Explanations

    terms related to orbital mechanics or space travel

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.11
    0.7%
    408
    +0.10
    0.6%
    376
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    408
    +0.11
    0.00
    276
    +0.10
    0.00
    79
    +0.10
    0.00
    Negative Logits
    ĥ½
    -1.97
     latter
    -1.87
     monoclonal
    -1.60
     differing
    -1.55
     pregnant
    -1.52
     particular
    -1.50
     manifest
    -1.50
    Ĥ
    -1.50
     promise
    -1.46
     polyclonal
    -1.45
    POSITIVE LOGITS
    castle
    1.95
    bank
    1.94
    "}](#
    1.78
    worthy
    1.77
    itat
    1.62
    opan
    1.61
    isión
    1.61
    boat
    1.60
    ism
    1.59
    geb
    1.59
    Activations Density 0.004%

    No Known Activations