© 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. 24969
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    443
    +0.13
    0.7%
    86
    +0.12
    0.6%
    53
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    42
    +0.13
    0.03
    28
    +0.12
    0.03
    489
    +0.12
    0.03
    Negative Logits
    lich
    -1.74
    igion
    -1.71
    baum
    -1.56
     describing
    -1.55
    pha
    -1.48
     chromatography
    -1.46
    aters
    -1.45
     masses
    -1.40
    roads
    -1.39
     referring
    -1.39
    POSITIVE LOGITS
    ppy
    1.60
    xit
    1.54
     normalize
    1.50
     than
    1.44
    ↵
    1.43
    undry
    1.41
    verted
    1.40
    ·¸
    1.39
     duplicate
    1.37
     Nova
    1.36
    Activations Density 0.008%

    No Known Activations

    This feature has no known activations.