© 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. 25796
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Kings"

    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
    457
    +0.13
    0.7%
    487
    +0.11
    0.6%
    325
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    192
    +0.13
    0.01
    487
    +0.11
    0.01
    94
    +0.11
    0.01
    Negative Logits
    acial
    -1.81
    EVER
    -1.75
    ,'"
    -1.68
     sudden
    -1.66
     abortions
    -1.54
    fection
    -1.54
    rapeutics
    -1.53
     anybody
    -1.53
    woke
    -1.53
     somebody
    -1.50
    POSITIVE LOGITS
    holm
    2.27
    fonts
    1.92
    creen
    1.90
    olver
    1.85
    bane
    1.80
    dimen
    1.80
    forge
    1.79
    bridge
    1.79
    cript
    1.79
     Canyon
    1.78
    Activations Density 0.013%

    No Known Activations