© 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. 26962
    Prev
    Next
    INDEX
    Explanations

    mention of the term "Pan."

    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
    369
    +0.18
    1.0%
    59
    +0.16
    0.9%
    156
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.18
    0.02
    411
    +0.16
    0.01
    416
    +0.13
    0.01
    Negative Logits
    ĥ½
    -2.20
    ł
    -2.15
    Ļ
    -2.07
    ļ
    -1.95
    ij
    -1.87
    Ŀ
    -1.86
    ¢
    -1.86
    Ĥ¬
    -1.81
    §
    -1.79
    ¥
    -1.77
    POSITIVE LOGITS
    ieux
    1.70
     feels
    1.66
     Trek
    1.64
    icked
    1.63
    fight
    1.62
    icum
    1.61
    icky
    1.55
    wave
    1.54
     tasted
    1.53
    iff
    1.51
    Activations Density 0.220%

    No Known Activations