© 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. 26179
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    400
    +0.14
    0.8%
    88
    +0.13
    0.8%
    420
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.14
    0.36
    23
    +0.13
    0.31
    494
    +0.12
    0.25
    Negative Logits
    mysql
    -1.48
    olan
    -1.43
    americ
    -1.40
    springframework
    -1.39
    hus
    -1.36
    cheon
    -1.36
    icing
    -1.35
    )\].
    -1.35
    phy
    -1.34
    sil
    -1.32
    POSITIVE LOGITS
    estone
    1.90
    gio
    1.75
    chitz
    1.60
     tuned
    1.53
    abouts
    1.49
    ittal
    1.42
     notices
    1.42
    :`
    1.40
     notice
    1.39
    habilitation
    1.37
    Activations Density 3.092%

    No Known Activations

    This feature has no known activations.