© 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. 25627
    Prev
    Next
    INDEX
    Explanations

    references to the plaintiff in legal documents

    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
    269
    +0.11
    0.6%
    376
    +0.10
    0.6%
    410
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    357
    +0.11
    0.02
    505
    +0.10
    0.02
    370
    +0.10
    0.01
    Negative Logits
     BGCOLOR
    -1.86
    ammar
    -1.71
    EOF
    -1.51
    dtd
    -1.48
    radiol
    -1.48
    lycer
    -1.43
    omers
    -1.39
    atz
    -1.38
    arner
    -1.37
    razil
    -1.33
    POSITIVE LOGITS
    piece
    1.78
    stru
    1.74
    pieces
    1.67
    uscript
    1.65
    istically
    1.60
    naire
    1.52
    net
    1.49
    urous
    1.45
     hall
    1.43
    ograp
    1.41
    Activations Density 0.012%

    No Known Activations