© 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. 30496
    Prev
    Next
    INDEX
    Explanations

    instances of the word "lecture" or its variations

    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
    +0.26
    1.5%
    376
    +0.12
    0.7%
    394
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    365
    +0.26
    0.01
    383
    +0.12
    0.01
    472
    +0.12
    0.01
    Negative Logits
    ĥ½
    -2.99
    IJ
    -2.66
    Į
    -2.63
    Ŀ
    -2.62
    ĨĴ
    -2.59
    Ķ
    -2.56
    ı
    -2.52
    ¯
    -2.48
    ¸
    -2.41
    Ń
    -2.38
    POSITIVE LOGITS
    case
    1.73
     ceil
    1.70
    stre
    1.67
     notes
    1.63
    ously
    1.60
    rs
    1.50
    veolar
    1.49
    minent
    1.46
    piece
    1.45
    oon
    1.45
    Activations Density 0.025%

    No Known Activations