© 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. 26502
    Prev
    Next
    INDEX
    Explanations

    references to a unified point or focal point in documents

    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
    +0.13
    0.7%
    439
    +0.12
    0.7%
    109
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    439
    +0.13
    0.01
    134
    +0.12
    0.01
    12
    +0.11
    0.01
    Negative Logits
    ĥ½
    -2.49
     distance
    -1.71
     mean
    -1.68
     dilated
    -1.67
     longer
    -1.62
     fair
    -1.60
    Ń
    -1.60
     entirety
    -1.57
    oping
    -1.51
     complete
    -1.51
    POSITIVE LOGITS
    ÅĽci
    2.37
    ÅĽÄĩ
    1.78
    ENTIAL
    1.73
    NP
    1.71
    ijk
    1.66
    PRESS
    1.66
    NER
    1.65
    phal
    1.61
    nik
    1.61
    press
    1.60
    Activations Density 0.005%

    No Known Activations