© 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. 30143
    Prev
    Next
    INDEX
    Explanations

    the word "ings" to identify plural forms or gerunds

    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
    +0.12
    0.7%
    279
    +0.12
    0.7%
    77
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    279
    +0.12
    0.01
    24
    +0.12
    0.01
    378
    +0.11
    0.01
    Negative Logits
     sexes
    -1.66
    others
    -1.63
     others
    -1.62
     myself
    -1.54
     majority
    -1.53
    twitter
    -1.51
    athing
    -1.45
    odies
    -1.43
    .?
    -1.42
     mocking
    -1.42
    POSITIVE LOGITS
    cript
    1.91
    aurus
    1.91
    CRIPT
    1.88
    FW
    1.86
    ist
    1.83
    naire
    1.71
    CI
    1.66
    erior
    1.61
    heet
    1.60
    ister
    1.58
    Activations Density 0.063%

    No Known Activations