© 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. 28627
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "undefined"

    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
    412
    +0.12
    0.7%
    260
    +0.11
    0.6%
    169
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    169
    +0.12
    0.01
    499
    +0.11
    0.01
    449
    +0.10
    0.01
    Negative Logits
    henyl
    -1.77
     thou
    -1.64
    idding
    -1.62
     hers
    -1.60
    uron
    -1.56
     yours
    -1.53
    isted
    -1.50
    anning
    -1.46
    ann
    -1.43
    you
    -1.43
    POSITIVE LOGITS
    cias
    2.20
    ière
    1.93
    pieces
    1.82
     sources
    1.80
    ¼
    1.76
    istics
    1.71
    uscript
    1.70
    cuts
    1.69
     perspectives
    1.64
    amento
    1.64
    Activations Density 0.409%

    No Known Activations