© 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. 29584
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Doug."

    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
    410
    +0.18
    1.0%
    59
    +0.14
    0.8%
    43
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.18
    0.01
    410
    +0.14
    0.01
    192
    +0.13
    0.02
    Negative Logits
     previous
    -1.70
     other
    -1.67
     subsequent
    -1.48
     fourth
    -1.46
    ı
    -1.41
     Nigerian
    -1.39
    prov
    -1.38
     future
    -1.37
    TRODUCTION
    -1.37
    vent
    -1.33
    POSITIVE LOGITS
    herty
    2.04
    ulence
    1.85
    lite
    1.73
    als
    1.73
    die
    1.70
    iej
    1.68
    lass
    1.64
    uet
    1.61
    ulent
    1.60
    illard
    1.56
    Activations Density 0.017%

    No Known Activations