© 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. 2-MLP-SM
    11. 22756
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and structures related to equations

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    92
    +0.17
    1.0%
    50
    +0.12
    0.7%
    475
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.17
    0.07
    92
    +0.12
    0.03
    50
    +0.12
    0.03
    Negative Logits
    isance
    -1.57
    blogger
    -1.45
     brute
    -1.39
     chant
    -1.38
     honour
    -1.35
    $.[]{
    -1.35
    vé
    -1.33
     abused
    -1.33
    .'"
    -1.32
     ':
    -1.31
    POSITIVE LOGITS
    ©
    2.11
    ¹
    1.87
    ®
    1.74
    irs
    1.72
    il
    1.71
    °
    1.69
    ¦
    1.68
    ĻĤ
    1.67
    ings
    1.67
    ¿
    1.66
    Activations Density 0.538%

    No Known Activations