© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27861
    Prev
    Next
    INDEX
    Explanations

    the German word "zu" indicating direction or focus

    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
    450
    +0.12
    0.7%
    332
    +0.12
    0.6%
    511
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    332
    +0.12
    0.01
    111
    +0.12
    0.01
    450
    +0.11
    0.01
    Negative Logits
    ij
    -1.57
     worth
    -1.50
    atum
    -1.47
    ments
    -1.45
     meaning
    -1.45
     alleged
    -1.43
    ged
    -1.43
    á̝
    -1.43
     actually
    -1.41
     recall
    -1.40
    POSITIVE LOGITS
    eto
    1.82
    aine
    1.78
    idelines
    1.61
    olta
    1.58
    imar
    1.52
    ilder
    1.49
    ENTIAL
    1.48
    ail
    1.46
    ylum
    1.45
    iji
    1.45
    Activations Density 0.068%

    No Known Activations