© 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. 2-MLP-SM
    11. 23214
    Prev
    Next
    INDEX
    Explanations

    the abbreviation "De" followed by numbers or certain patterns associated with it

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    156
    +0.29
    1.6%
    27
    +0.11
    0.6%
    446
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    446
    +0.29
    0.02
    140
    +0.11
    0.02
    27
    +0.11
    0.01
    Negative Logits
    éd
    -1.82
    anine
    -1.82
    éri
    -1.69
    lement
    -1.68
    át
    -1.65
    lem
    -1.64
    ène
    -1.60
    ép
    -1.60
    ienne
    -1.60
    ésident
    -1.58
    POSITIVE LOGITS
     questions
    1.61
     hours
    1.54
     hell
    1.52
     scenarios
    1.51
    ations
    1.50
    ¹
    1.49
    ually
    1.46
    ibilities
    1.45
     directions
    1.43
     breeds
    1.41
    Activations Density 0.162%

    No Known Activations