© 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. 25935
    Prev
    Next
    INDEX
    Explanations

    instances of the word "assets."

    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
    376
    +0.14
    0.9%
    405
    +0.13
    0.8%
    365
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    405
    +0.14
    0.01
    365
    +0.13
    0.01
    425
    +0.13
    0.01
    Negative Logits
    Īĺ
    -2.24
    ĨĴ
    -2.09
    ²
    -2.09
    «
    -1.98
    ľĵ
    -1.98
    ¿½
    -1.95
    Ĥ
    -1.88
    ´
    -1.88
    ĵ
    -1.86
    Ļª
    -1.84
    POSITIVE LOGITS
    pieces
    1.96
    ég
    1.90
    erve
    1.89
    ÅĽci
    1.88
    castle
    1.79
    eries
    1.74
    plots
    1.70
    sheet
    1.70
    guard
    1.69
    pool
    1.68
    Activations Density 0.011%

    No Known Activations