© 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. 30117
    Prev
    Next
    INDEX
    Explanations

    the word "outs" and related phrases indicating exits or conclusions in various contexts

    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
    144
    +0.16
    0.9%
    376
    +0.12
    0.7%
    86
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    144
    +0.16
    0.02
    86
    +0.12
    0.02
    212
    +0.11
    0.02
    Negative Logits
     preponderance
    -1.63
    ¿½
    -1.63
     ease
    -1.54
    ytes
    -1.47
    lux
    -1.43
    ben
    -1.41
    rapeut
    -1.39
     small
    -1.39
     slightest
    -1.36
    auc
    -1.35
    POSITIVE LOGITS
    emente
    1.93
    ue
    1.83
    wick
    1.71
    ovich
    1.68
    ist
    1.65
    ources
    1.64
    isten
    1.63
    iston
    1.60
    nier
    1.58
    iewicz
    1.57
    Activations Density 0.020%

    No Known Activations