© 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. 29266
    Prev
    Next
    INDEX
    Explanations

    references to the genre of rap music

    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
    +0.16
    0.9%
    2
    +0.16
    0.9%
    156
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.16
    0.01
    59
    +0.16
    0.01
    2
    +0.10
    0.01
    Negative Logits
    ĥ½
    -2.33
    ĵ
    -1.97
    ¯
    -1.93
    ¿
    -1.90
    ĸ´
    -1.90
    Ń
    -1.88
    ķ
    -1.82
    Ŀ
    -1.80
    §
    -1.74
    ľĵ
    -1.73
    POSITIVE LOGITS
    ist
    1.95
    hael
    1.84
    ifer
    1.77
     legend
    1.76
    uet
    1.75
    forge
    1.57
    ists
    1.54
    craft
    1.52
    dom
    1.50
    ue
    1.48
    Activations Density 0.018%

    No Known Activations