© 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. 25842
    Prev
    Next
    INDEX
    Explanations

    references to the name "Max."

    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
    369
    +0.18
    1.0%
    156
    +0.15
    0.9%
    376
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    289
    +0.18
    0.02
    363
    +0.15
    0.01
    317
    +0.14
    0.01
    Negative Logits
    ĥ½
    -1.81
    ı
    -1.77
    ¢
    -1.66
    §
    -1.65
     hers
    -1.65
    Ļª
    -1.62
    ĸ´
    -1.61
    ¿½
    -1.60
    ears
    -1.59
    »¿
    -1.51
    POSITIVE LOGITS
    iej
    2.00
    imal
    1.82
    hole
    1.77
    imize
    1.74
    ious
    1.69
    chitz
    1.66
    ikel
    1.62
    lane
    1.60
    field
    1.58
    icillin
    1.57
    Activations Density 0.037%

    No Known Activations