© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 26847
    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
    212
    +0.13
    0.7%
    268
    +0.12
    0.7%
    408
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.13
    0.36
    23
    +0.12
    0.31
    494
    +0.11
    0.25
    Negative Logits
    iab
    -1.54
     time
    -1.53
    oslav
    -1.52
    opters
    -1.50
    chaft
    -1.43
     succeeded
    -1.38
    ometers
    -1.36
    ocent
    -1.34
    cket
    -1.32
    pez
    -1.31
    POSITIVE LOGITS
    $-
    1.61
     convenience
    1.57
     posture
    1.52
    &&\
    1.51
    lights
    1.47
     sidebar
    1.39
    \(
    1.39
    [**
    1.37
    \\
    1.37
     recreational
    1.35
    Activations Density 3.082%

    No Known Activations

    This feature has no known activations.