© 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. 25485
    Prev
    Next
    INDEX
    Explanations

    references to health and promotion-related organizations and initiatives

    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
    319
    +0.13
    0.7%
    95
    +0.11
    0.6%
    260
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    438
    +0.13
    0.39
    53
    +0.11
    0.42
    56
    +0.11
    0.11
    Negative Logits
    umatic
    -1.69
    Ń
    -1.65
    ème
    -1.61
    uximab
    -1.59
    ._
    -1.56
    _."
    -1.55
    izoph
    -1.55
    Emphasis
    -1.54
    §
    -1.54
    ifax
    -1.54
    POSITIVE LOGITS
     Office
    1.70
    aded
    1.47
     bureaucracy
    1.46
     Order
    1.46
     No
    1.46
     print
    1.45
     Not
    1.39
     Just
    1.39
     Hon
    1.38
     baggage
    1.35
    Activations Density 4.624%

    No Known Activations