© 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. 28279
    Prev
    Next
    INDEX
    Explanations

    the word "unparalleled."

    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
    406
    +0.13
    0.8%
    256
    +0.13
    0.7%
    314
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    406
    +0.13
    0.01
    256
    +0.13
    0.01
    314
    +0.13
    0.01
    Negative Logits
    ´
    -3.15
    ĸ´
    -3.12
    ij
    -3.08
    ĨĴ
    -3.03
    Ĥ¬
    -2.97
    ·¸
    -2.94
    ²
    -2.92
    Ĩ
    -2.78
    ¿½
    -2.73
    ĺ
    -2.72
    POSITIVE LOGITS
    wick
    1.85
    stadt
    1.66
    stown
    1.65
    ÅĽci
    1.62
    force
    1.61
    cule
    1.58
    edly
    1.57
    rote
    1.56
    ifornia
    1.55
    ÅĽÄĩ
    1.54
    Activations Density 0.047%

    No Known Activations