© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 28137
    Prev
    Next
    INDEX
    Explanations

    repeated mentions of "North Dakota"

    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
    369
    +0.17
    1.0%
    457
    +0.14
    0.8%
    31
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    31
    +0.17
    0.04
    181
    +0.14
    0.03
    457
    +0.12
    0.03
    Negative Logits
    zed
    -1.54
    ĥ½
    -1.53
    ção
    -1.52
    tet
    -1.48
    cluding
    -1.47
    ection
    -1.45
    hers
    -1.42
    hern
    -1.39
    nlm
    -1.39
    ĩ
    -1.38
    POSITIVE LOGITS
    umberland
    1.79
    wick
    1.67
    bolt
    1.60
     theme
    1.59
     depends
    1.58
    craft
    1.58
    rop
    1.56
    wind
    1.55
    ward
    1.54
    field
    1.54
    Activations Density 1.453%

    No Known Activations