© 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. 29617
    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
    206
    +0.14
    0.8%
    465
    +0.13
    0.7%
    476
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    402
    +0.14
    0.15
    26
    +0.13
    0.14
    199
    +0.12
    0.14
    Negative Logits
    Ĭ
    -3.69
    Ł
    -3.66
    ĻĤ
    -3.65
    ¨
    -3.65
    İ
    -3.54
    Ĩ
    -3.50
    ¼
    -3.40
    «
    -3.35
    į
    -3.35
    ½
    -3.34
    POSITIVE LOGITS
    ui
    1.51
     interest
    1.47
    grounds
    1.45
    oi
    1.43
    &$
    1.43
    raising
    1.35
     experimental
    1.31
     tid
    1.31
    POR
    1.29
    oz
    1.28
    Activations Density 0.274%

    No Known Activations

    This feature has no known activations.