© 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. 30546
    Prev
    Next
    INDEX
    Explanations

    words related to military ranks or titles

    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
    443
    +0.14
    0.8%
    376
    +0.13
    0.8%
    59
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.14
    0.01
    111
    +0.13
    0.01
    443
    +0.12
    0.01
    Negative Logits
     faire
    -1.66
    ĵ
    -1.65
    "?"
    -1.62
     mediator
    -1.57
     son
    -1.52
    izes
    -1.49
     sino
    -1.47
     después
    -1.46
     maternal
    -1.45
     particular
    -1.45
    POSITIVE LOGITS
    antine
    2.12
    idor
    1.89
    itude
    1.85
    shots
    1.79
    adier
    1.76
    ouin
    1.75
    ename
    1.75
    itte
    1.71
    ings
    1.67
    uet
    1.63
    Activations Density 0.047%

    No Known Activations