© 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. 25767
    Prev
    Next
    INDEX
    Explanations

    words that indicate frequency or repetition

    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
    376
    +0.13
    0.7%
    23
    +0.13
    0.7%
    156
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    257
    +0.13
    0.04
    135
    +0.13
    0.04
    409
    +0.11
    0.04
    Negative Logits
    etted
    -1.65
    rown
    -1.65
     itself
    -1.61
    illard
    -1.61
     potential
    -1.60
    enson
    -1.59
    ARK
    -1.50
    ark
    -1.48
    INK
    -1.43
     themselves
    -1.40
    POSITIVE LOGITS
    Ļª
    2.28
    chitz
    1.94
    cology
    1.73
    oscopic
    1.55
    abouts
    1.51
     times
    1.50
    ocations
    1.43
    °
    1.40
     voiced
    1.36
     paused
    1.32
    Activations Density 0.130%

    No Known Activations