© 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. 30654
    Prev
    Next
    INDEX
    Explanations

    references to royalty, specifically the word "Prince" and its variations

    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
    +0.18
    1.1%
    376
    +0.14
    0.8%
    389
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    389
    +0.18
    0.01
    450
    +0.14
    0.01
    174
    +0.13
    0.01
    Negative Logits
    Ļª
    -3.28
    ĥ½
    -3.02
    IJ
    -2.90
    Ń
    -2.81
    ´
    -2.68
    ĺ
    -2.67
    Ĵ
    -2.65
    ķ
    -2.52
    Ĥ¬
    -2.50
    ¬
    -2.47
    POSITIVE LOGITS
    doms
    2.25
    smen
    1.99
    craft
    1.85
    holder
    1.78
    folk
    1.73
    idium
    1.70
    ÃŃf
    1.70
    zilla
    1.69
    aho
    1.67
    mong
    1.57
    Activations Density 0.014%

    No Known Activations