© 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 EvalsExportsAPI 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. 28887
    Prev
    Next
    INDEX
    Explanations

    words related to closing or ending events

    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
    +0.20
    1.1%
    503
    +0.12
    0.7%
    144
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    503
    +0.20
    0.01
    293
    +0.12
    0.01
    239
    +0.11
    0.01
    Negative Logits
    »
    -1.58
     monoton
    -1.56
    ¦
    -1.39
    ones
    -1.39
    Ļª
    -1.38
    called
    -1.36
    acial
    -1.35
     Dev
    -1.34
     decreasing
    -1.31
    CLA
    -1.31
    POSITIVE LOGITS
    fecture
    1.79
    emption
    1.71
    itor
    1.63
     party
    1.62
     apparatus
    1.58
    mpi
    1.54
    hower
    1.52
    ftware
    1.52
    eer
    1.49
    ulate
    1.45
    Activations Density 0.013%

    No Known Activations