© 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. 25765
    Prev
    Next
    INDEX
    Explanations

    comparative phrases indicating "more than" or "greater than" in various contexts

    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
    360
    +0.12
    0.7%
    461
    +0.11
    0.6%
    500
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    508
    +0.12
    0.07
    208
    +0.11
    0.07
    221
    +0.11
    0.07
    Negative Logits
    Ĥ
    -2.12
    ¼
    -2.09
    ŀ
    -1.98
    ĸ´
    -1.97
    ©
    -1.96
    ·¸
    -1.95
    ¥
    -1.92
    Ń
    -1.90
    ī
    -1.89
    ±
    -1.88
    POSITIVE LOGITS
    viv
    1.92
    vist
    1.82
    ctor
    1.76
    aeda
    1.64
    ukin
    1.51
      ↵
    1.49
    %"}
    1.47
    [{
    1.47
    '">
    1.47
    eon
    1.46
    Activations Density 0.131%

    No Known Activations