© 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. 29129
    Prev
    Next
    INDEX
    Explanations

    references to credit or identification cards

    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
    +0.14
    0.8%
    376
    +0.14
    0.8%
    194
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    194
    +0.14
    0.02
    435
    +0.14
    0.02
    468
    +0.12
    0.01
    Negative Logits
    ĵ
    -2.01
    ĥ½
    -1.96
    Ĥ
    -1.86
    ľ
    -1.85
    ¿
    -1.85
    ı
    -1.78
    IJ
    -1.77
    ĨĴ
    -1.76
     snow
    -1.70
    ments
    -1.67
    POSITIVE LOGITS
    igan
    2.56
    iff
    2.12
    ucci
    2.09
    oso
    2.04
    holder
    2.02
    opan
    1.94
    esan
    1.92
    ume
    1.90
    iem
    1.89
    iot
    1.75
    Activations Density 0.010%

    No Known Activations