© 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. 30268
    Prev
    Next
    INDEX
    Explanations

    phrases related to towing and hitch systems

    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
    111
    +0.15
    0.8%
    455
    +0.12
    0.7%
    38
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.15
    0.01
    257
    +0.12
    0.01
    283
    +0.12
    0.01
    Negative Logits
    ção
    -1.53
    eks
    -1.53
    eration
    -1.53
     reputation
    -1.49
     consent
    -1.47
     systematic
    -1.47
     unanimous
    -1.44
     disclosure
    -1.43
    fts
    -1.41
     sweat
    -1.40
    POSITIVE LOGITS
    nuts
    1.88
     apart
    1.72
    {}{
    1.71
    pie
    1.71
    ariate
    1.69
    shots
    1.62
    itzer
    1.60
    horn
    1.60
    ableness
    1.59
    argument
    1.53
    Activations Density 0.013%

    No Known Activations