© 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. 28970
    Prev
    Next
    INDEX
    Explanations

    references to various authentication mechanisms

    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
    156
    +0.27
    1.7%
    376
    +0.15
    0.9%
    113
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    270
    +0.27
    0.01
    82
    +0.15
    0.01
    156
    +0.10
    0.01
    Negative Logits
    woke
    -1.91
    uffling
    -1.82
    unnumbered
    -1.71
    sed
    -1.58
    awk
    -1.57
    >(
    -1.56
    >`
    -1.55
    comm
    -1.50
    IJ
    -1.49
    :=
    -1.44
    POSITIVE LOGITS
    ulate
    1.83
     errors
    1.82
    nier
    1.75
     cavity
    1.66
     centres
    1.62
     centers
    1.61
     appliances
    1.60
     schemes
    1.55
     cavities
    1.55
    sters
    1.54
    Activations Density 0.012%

    No Known Activations