© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 28252
    Prev
    Next
    INDEX
    Explanations

    references to training and qualifications in various contexts

    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
    376
    +0.14
    0.8%
    416
    +0.13
    0.7%
    428
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.14
    0.34
    151
    +0.13
    0.33
    434
    +0.11
    0.29
    Negative Logits
     following
    -1.71
     collabor
    -1.49
     investing
    -1.48
    Wave
    -1.43
     Peer
    -1.36
     Generation
    -1.34
     generations
    -1.34
     contacting
    -1.34
     Enron
    -1.33
    ervice
    -1.31
    POSITIVE LOGITS
    Ń
    2.92
    ŀ
    2.92
    į
    2.90
    ½
    2.69
    ı
    2.52
    ¯
    2.51
    Ģ
    2.48
    ĵ
    2.47
    ¬
    2.44
    ¥
    2.42
    Activations Density 3.196%

    No Known Activations