© 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 EvalsExportsAPI 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. 28581
    Prev
    Next
    INDEX
    Explanations

    lists, guidelines, and instructions regarding safety and precautions

    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
    204
    +0.12
    0.7%
    496
    +0.12
    0.7%
    208
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    438
    +0.12
    0.40
    53
    +0.12
    0.42
    56
    +0.10
    0.11
    Negative Logits
    razil
    -1.71
    lut
    -1.70
    ocar
    -1.66
    Ĥ
    -1.64
    onin
    -1.63
    $]{};
    -1.57
    imar
    -1.56
    ij
    -1.54
    ]{
    -1.53
    ox
    -1.53
    POSITIVE LOGITS
     herself
    1.67
     scenes
    1.63
    ES
    1.61
     itself
    1.53
     theirs
    1.50
     related
    1.48
    /"
    1.45
    etc
    1.42
     appointments
    1.40
     lies
    1.37
    Activations Density 4.652%

    No Known Activations