© 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. 28100
    Prev
    Next
    INDEX
    Explanations

    references to preschool education and related early childhood terms

    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
    +0.20
    1.1%
    102
    +0.12
    0.7%
    277
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.20
    0.01
    451
    +0.12
    0.01
    40
    +0.10
    0.01
    Negative Logits
    ¥
    -1.93
    IJ
    -1.80
    ³
    -1.75
    ¬
    -1.68
    Ĺ
    -1.60
    ¾
    -1.56
    esides
    -1.56
    ¯
    -1.55
    Ĵ
    -1.54
     vain
    -1.51
    POSITIVE LOGITS
    à±į
    1.76
    "}](#
    1.67
    eries
    1.64
    ercase
    1.53
    doctoral
    1.51
    print
    1.50
    eri
    1.49
    lit
    1.47
     ()
    1.46
    ↵ ↵
    1.43
    Activations Density 0.024%

    No Known Activations