© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 30906
    Prev
    Next
    INDEX
    Explanations

    sequences of characters representing non-word elements in code or markup

    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
    67
    +0.13
    0.7%
    40
    +0.13
    0.7%
    101
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    279
    +0.13
    0.05
    76
    +0.13
    0.06
    53
    +0.13
    0.05
    Negative Logits
    abouts
    -1.76
    ito
    -1.69
    rell
    -1.52
    enders
    -1.48
    iÄĩ
    -1.48
    offs
    -1.44
    itudes
    -1.44
    ème
    -1.43
    oves
    -1.43
    itor
    -1.36
    POSITIVE LOGITS
    ĥ½
    2.07
    ĻĤ
    1.99
    Īĺ
    1.98
    ij
    1.96
    Ģ
    1.90
    ħ
    1.88
    ľĵ
    1.81
    ª
    1.77
    ł
    1.73
    ¬
    1.72
    Activations Density 0.110%

    No Known Activations