© 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. 29371
    Prev
    Next
    INDEX
    Explanations

    mentions of judges and magistrates

    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
    505
    +0.14
    0.8%
    132
    +0.12
    0.7%
    454
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    505
    +0.14
    0.03
    132
    +0.12
    0.02
    153
    +0.10
    0.02
    Negative Logits
    ĥ½
    -3.15
    ´
    -2.87
    ·¸
    -2.74
    ŀ
    -2.69
    ij
    -2.69
    Ķ
    -2.68
    Ħ
    -2.66
    ¯
    -2.63
    ¬
    -2.62
    Ī
    -2.57
    POSITIVE LOGITS
    pieces
    2.02
    cript
    1.92
    doms
    1.85
    wick
    1.82
    piece
    1.79
    ÃŃf
    1.76
     himself
    1.71
    amente
    1.69
    lists
    1.64
    heet
    1.64
    Activations Density 0.013%

    No Known Activations