© 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. 25078
    Prev
    Next
    INDEX
    Explanations

    references to baseline measurements in various contexts

    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
    156
    +0.23
    1.3%
    376
    +0.14
    0.8%
    308
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    163
    +0.23
    0.01
    308
    +0.14
    0.01
    299
    +0.11
    0.01
    Negative Logits
    ĥ½
    -3.53
    Ĵ
    -3.34
    §
    -2.95
    ¸
    -2.92
    ©
    -2.89
    Ķ
    -2.88
    ·
    -2.84
    ĵ
    -2.66
    Ĥ
    -2.65
    ¯
    -2.64
    POSITIVE LOGITS
    isations
    1.77
     positions
    1.69
     situation
    1.56
    entes
    1.53
     needs
    1.52
    positions
    1.46
    istes
    1.44
    ist
    1.41
    ifs
    1.41
    dates
    1.39
    Activations Density 0.015%

    No Known Activations