© 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. 30971
    Prev
    Next
    INDEX
    Explanations

    abbreviations or acronyms related to networking or technology

    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
    301
    +0.13
    0.7%
    412
    +0.12
    0.6%
    376
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    301
    +0.13
    0.01
    347
    +0.12
    0.01
    412
    +0.12
    0.01
    Negative Logits
    ĥ½
    -2.01
     hurry
    -1.71
     lean
    -1.62
    anium
    -1.59
     streak
    -1.58
    imony
    -1.58
    ances
    -1.57
     enough
    -1.56
    ĭ
    -1.54
    ¼
    -1.54
    POSITIVE LOGITS
    PLICATION
    1.90
    ariate
    1.72
    ios
    1.61
    sizeof
    1.59
    venue
    1.56
    clonal
    1.55
    iew
    1.51
    1
    1.50
    CoV
    1.49
    :`
    1.47
    Activations Density 0.165%

    No Known Activations