© 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. 29491
    Prev
    Next
    INDEX
    Explanations

    references to shopping activities

    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
    +0.14
    0.9%
    173
    +0.14
    0.9%
    29
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    173
    +0.14
    0.03
    80
    +0.14
    0.02
    346
    +0.13
    0.02
    Negative Logits
    ĥ½
    -1.95
    ľ
    -1.94
    Į
    -1.93
    §
    -1.85
    Ļª
    -1.85
    ¯
    -1.78
    ı
    -1.68
     '</
    -1.68
    «
    -1.64
    rophic
    -1.63
    POSITIVE LOGITS
    place
    1.80
    yards
    1.76
     regimes
    1.69
    fors
    1.62
     analyst
    1.61
     habits
    1.54
     offense
    1.51
    houses
    1.50
     gaps
    1.49
     channels
    1.48
    Activations Density 0.022%

    No Known Activations