© 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 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. 28518
    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
    433
    +0.14
    0.8%
    226
    +0.13
    0.7%
    468
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    494
    +0.14
    0.45
    209
    +0.13
    0.29
    402
    +0.12
    0.26
    Negative Logits
    OME
    -1.61
     skills
    -1.51
    documentclass
    -1.47
     heal
    -1.44
    ically
    -1.41
     confront
    -1.40
     toug
    -1.40
     govern
    -1.40
     procedures
    -1.38
     cure
    -1.32
    POSITIVE LOGITS
    ¾
    1.69
    "}](#
    1.59
    supplementary
    1.54
    ĨĴ
    1.50
     NSString
    1.48
    rum
    1.44
    ije
    1.41
    icum
    1.39
    ²
    1.39
    )_
    1.38
    Activations Density 1.568%

    No Known Activations

    This feature has no known activations.