© 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. 25859
    Prev
    Next
    INDEX
    Explanations

    mentions of "rum."

    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
    68
    +0.14
    0.8%
    501
    +0.12
    0.7%
    362
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    68
    +0.14
    0.02
    501
    +0.12
    0.02
    480
    +0.12
    0.01
    Negative Logits
    ĭ
    -1.97
    ĥ½
    -1.85
    ANC
    -1.77
    ANCE
    -1.67
    ļ
    -1.66
    ij
    -1.61
    Į
    -1.56
    ctica
    -1.56
    >()
    -1.53
     '</
    -1.51
    POSITIVE LOGITS
    eless
    1.86
    mage
    1.83
     traditions
    1.73
    enez
    1.72
    eration
    1.69
    emaker
    1.64
    ération
    1.60
    fire
    1.58
     legends
    1.56
    ieux
    1.51
    Activations Density 0.017%

    No Known Activations