© 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. 26665
    Prev
    Next
    INDEX
    Explanations

    commands or functions related to setting parameters or configurations

    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
    +0.16
    0.9%
    380
    +0.11
    0.6%
    144
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    380
    +0.16
    0.03
    252
    +0.11
    0.03
    144
    +0.11
    0.03
    Negative Logits
     \\
    -1.95
    \\
    -1.83
    $}
    -1.80
     not
    -1.70
    "}**).
    -1.70
    )\\
    -1.65
    _"
    -1.58
    ;"
    -1.54
    }\\
    -1.52
    itting
    -1.51
    POSITIVE LOGITS
    pile
    1.98
    ions
    1.94
    ups
    1.78
    tees
    1.77
    abad
    1.72
    iative
    1.71
    cule
    1.71
    istical
    1.71
    âĢij
    1.68
    arian
    1.68
    Activations Density 0.828%

    No Known Activations