© 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. 29507
    Prev
    Next
    INDEX
    Explanations

    patterns related to the term "usage."

    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
    +0.15
    0.9%
    376
    +0.13
    0.8%
    241
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    178
    +0.15
    0.01
    241
    +0.13
    0.01
    89
    +0.13
    0.01
    Negative Logits
    ubicin
    -1.73
    EVER
    -1.69
    ITY
    -1.60
     CONSEQUENTIAL
    -1.55
    )$)
    -1.52
    áĢ¯
    -1.51
    ndef
    -1.49
    *>
    -1.48
    YA
    -1.46
    Simplify
    -1.44
    POSITIVE LOGITS
     area
    2.09
     appears
    1.99
     tracker
    1.72
     centers
    1.72
    cript
    1.61
     data
    1.61
     view
    1.61
    chart
    1.60
     areas
    1.59
     appear
    1.59
    Activations Density 0.010%

    No Known Activations