© 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 EvalsExportsAPI 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. 29134
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals, particularly those named Gab and Ug

    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
    +0.18
    1.1%
    59
    +0.14
    0.8%
    339
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.18
    0.01
    111
    +0.14
    0.01
    339
    +0.12
    0.01
    Negative Logits
    naments
    -1.74
     ago
    -1.72
    Ļª
    -1.72
    wered
    -1.70
    ¿½
    -1.70
    igm
    -1.59
    isation
    -1.50
     mercy
    -1.50
     angels
    -1.47
     vengeance
    -1.45
    POSITIVE LOGITS
    ño
    1.65
    stones
    1.63
    opan
    1.62
    ulous
    1.59
    illard
    1.57
    itage
    1.55
    win
    1.54
    ardo
    1.50
    pson
    1.50
    uer
    1.49
    Activations Density 0.011%

    No Known Activations