© 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. 29226
    Prev
    Next
    INDEX
    Explanations

    references to various schemes

    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
    +0.19
    1.1%
    376
    +0.16
    0.9%
    196
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    196
    +0.19
    0.01
    483
    +0.16
    0.01
    295
    +0.11
    0.01
    Negative Logits
    jours
    -1.62
     guts
    -1.61
     latter
    -1.53
    ze
    -1.49
    woke
    -1.47
    sole
    -1.43
    deal
    -1.38
    EVER
    -1.38
    InstanceState
    -1.38
     rain
    -1.38
    POSITIVE LOGITS
    imetry
    1.74
    atted
    1.74
    atically
    1.72
    obi
    1.70
    etary
    1.69
     appears
    1.67
    ats
    1.64
    erna
    1.63
    atics
    1.62
    ulator
    1.62
    Activations Density 0.011%

    No Known Activations