© 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. 25127
    Prev
    Next
    INDEX
    Explanations

    references to volume measurements and related terminology

    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
    376
    +0.14
    0.8%
    510
    +0.13
    0.7%
    256
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    419
    +0.14
    0.01
    440
    +0.13
    0.01
    53
    +0.10
    0.01
    Negative Logits
     backdrop
    -1.89
     our
    -1.56
     true
    -1.56
    ichi
    -1.50
     false
    -1.49
     appellants
    -1.47
     visitor
    -1.44
     sight
    -1.44
     us
    -1.43
    velopment
    -1.42
    POSITIVE LOGITS
    ģ
    1.90
    ¿½
    1.90
    umetric
    1.89
    istar
    1.74
    ĻĤ
    1.72
    ague
    1.71
    ĥ½
    1.68
    Ĭ
    1.65
    aq
    1.62
    hou
    1.62
    Activations Density 4.676%

    No Known Activations