© 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. 30500
    Prev
    Next
    INDEX
    Explanations

    words associated with abundance and scarcity

    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
    +0.33
    1.9%
    376
    +0.18
    1.1%
    148
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.33
    0.01
    135
    +0.18
    0.01
    432
    +0.14
    0.01
    Negative Logits
    lew
    -1.59
    openh
    -1.55
    las
    -1.53
    že
    -1.51
    anson
    -1.51
    lop
    -1.51
    derer
    -1.50
    üller
    -1.50
    feren
    -1.46
    rov
    -1.43
    POSITIVE LOGITS
     enough
    1.92
    ł
    1.72
    ĻĤ
    1.55
    Ģ
    1.55
     seeing
    1.54
     times
    1.51
     reads
    1.49
     ones
    1.47
     amounts
    1.45
     (\>
    1.39
    Activations Density 0.013%

    No Known Activations