© 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. 26111
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to a educational or academic context

    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
    429
    +0.15
    0.9%
    369
    +0.12
    0.7%
    139
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    429
    +0.15
    0.02
    332
    +0.12
    0.02
    383
    +0.11
    0.02
    Negative Logits
    ľĵ
    -2.54
    ¿½
    -2.52
    ¡
    -2.39
    ij
    -2.26
    Ĩ
    -2.25
    Ł
    -2.24
    ¦
    -2.12
    IJ
    -2.11
    Īĺ
    -2.07
    »
    -2.05
    POSITIVE LOGITS
    ruptcy
    1.73
    hold
    1.64
    idone
    1.63
    pdev
    1.59
    ios
    1.59
    plots
    1.58
     schemes
    1.53
    FC
    1.51
    documentclass
    1.49
    anguage
    1.48
    Activations Density 0.011%

    No Known Activations