© 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. 25838
    Prev
    Next
    INDEX
    Explanations

    references to electrodes in a technical or scientific context

    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
    156
    +0.26
    1.6%
    376
    +0.14
    0.9%
    446
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    446
    +0.26
    0.01
    219
    +0.14
    0.01
    158
    +0.12
    0.01
    Negative Logits
    ĥ½
    -1.90
     happier
    -1.59
    edes
    -1.57
    EVER
    -1.46
    Ķ
    -1.43
    ĵ
    -1.43
     Empire
    -1.41
    ı
    -1.41
    %=
    -1.39
     its
    -1.35
    POSITIVE LOGITS
    leen
    2.03
     casts
    1.69
     area
    1.68
    calc
    1.64
    rant
    1.57
    notes
    1.49
    grams
    1.47
    ucci
    1.46
    spot
    1.46
    ium
    1.45
    Activations Density 0.069%

    No Known Activations