© 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. 30810
    Prev
    Next
    INDEX
    Explanations

    references to blogging

    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
    +0.18
    1.0%
    82
    +0.17
    1.0%
    173
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    173
    +0.18
    0.04
    156
    +0.17
    0.03
    82
    +0.14
    0.03
    Negative Logits
    ving
    -1.76
     swimming
    -1.68
    ément
    -1.60
     dancing
    -1.59
    uge
    -1.55
    ifi
    -1.54
    arte
    -1.52
    igo
    -1.51
    ionization
    -1.50
    zing
    -1.49
    POSITIVE LOGITS
    redients
    1.88
    ulate
    1.69
     purposes
    1.69
    KES
    1.65
    ulates
    1.61
     properties
    1.57
     practices
    1.52
     techniques
    1.48
     background
    1.48
    lass
    1.47
    Activations Density 0.064%

    No Known Activations