© 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. 31112
    Prev
    Next
    INDEX
    Explanations

    terms related to peripheral regions or aspects

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    377
    +0.15
    0.8%
    376
    +0.13
    0.7%
    156
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    339
    +0.15
    0.01
    341
    +0.13
    0.01
    377
    +0.13
    0.01
    Negative Logits
    mber
    -1.86
    ĥ½
    -1.76
    ÑĢоÑģ
    -1.56
    ronic
    -1.50
    rapeut
    -1.47
     mean
    -1.46
    herty
    -1.42
    Ķ
    -1.41
    eks
    -1.40
    rate
    -1.31
    POSITIVE LOGITS
    iss
    1.69
     aside
    1.62
     blindness
    1.50
    ++,
    1.48
    issance
    1.46
     endings
    1.43
    holes
    1.42
    ity
    1.41
     holes
    1.40
     veins
    1.39
    Activations Density 0.036%

    No Known Activations