© 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. 26499
    Prev
    Next
    INDEX
    Explanations

    words related to cancer and its various aspects

    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
    156
    +0.19
    1.1%
    321
    +0.12
    0.7%
    453
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.19
    0.03
    61
    +0.12
    0.02
    88
    +0.10
    0.02
    Negative Logits
    ¯
    -2.67
    Ŀ
    -2.52
    ĺ
    -2.37
    ĥ½
    -2.29
    ı
    -2.15
    ĨĴ
    -2.12
    Į
    -2.12
    ĸ´
    -2.10
    IJ
    -2.05
    ľ
    -2.04
    POSITIVE LOGITS
     pose
    1.56
     centers
    1.54
     amounts
    1.49
     risks
    1.47
     poses
    1.46
     puzzles
    1.44
     patents
    1.43
     liabilities
    1.38
     stems
    1.36
    ious
    1.35
    Activations Density 0.978%

    No Known Activations