© 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. 26597
    Prev
    Next
    INDEX
    Explanations

    specific numerical values or data entries

    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
    245
    +0.13
    0.7%
    182
    +0.12
    0.7%
    58
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    307
    +0.13
    0.05
    58
    +0.12
    0.04
    245
    +0.12
    0.04
    Negative Logits
    hesis
    -1.90
    imony
    -1.83
    case
    -1.69
    atility
    -1.52
    sein
    -1.49
    derr
    -1.49
    ategy
    -1.43
    hav
    -1.41
    ingale
    -1.41
     believe
    -1.36
    POSITIVE LOGITS
    Ĵ
    4.06
    ł
    3.94
    ĸ
    3.72
    IJ
    3.61
    Ĥ
    3.52
    ¦
    3.42
    ª
    3.41
    ¡
    3.41
    ©
    3.41
    ķ
    3.39
    Activations Density 0.090%

    No Known Activations