© 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. 25279
    Prev
    Next
    INDEX
    Explanations

    references to measures of quality or superiority

    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
    131
    +0.13
    0.7%
    269
    +0.12
    0.7%
    156
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    131
    +0.13
    0.03
    285
    +0.12
    0.02
    277
    +0.11
    0.03
    Negative Logits
    epid
    -1.86
    ZO
    -1.57
    ³
    -1.53
    anco
    -1.49
    uster
    -1.44
    ·¸
    -1.42
     altogether
    -1.41
     most
    -1.40
    ±
    -1.35
    itian
    -1.35
    POSITIVE LOGITS
    rics
    1.62
    imated
    1.54
    enn
    1.51
     stakes
    1.49
    het
    1.46
     (>
    1.42
     hur
    1.41
    quarters
    1.38
     ones
    1.38
     Father
    1.33
    Activations Density 0.018%

    No Known Activations