© 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. 28413
    Prev
    Next
    INDEX
    Explanations

    references to specific models or types of products

    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
    469
    +0.12
    0.7%
    410
    +0.10
    0.6%
    433
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    469
    +0.12
    0.01
    370
    +0.10
    0.01
    344
    +0.10
    0.01
    Negative Logits
    »¿
    -2.13
    ¿½
    -1.95
     Anyway
    -1.83
    ĨĴ
    -1.79
    ĥ½
    -1.76
    ´
    -1.69
    Anyway
    -1.64
    ance
    -1.63
    ĻĤ
    -1.61
     nasty
    -1.58
    POSITIVE LOGITS
    wagen
    1.91
    aurus
    1.85
    framework
    1.77
    nement
    1.75
    enos
    1.72
    xon
    1.63
    cule
    1.62
    finder
    1.62
    clus
    1.59
    volt
    1.57
    Activations Density 0.100%

    No Known Activations