© 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. 31138
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "rep"

    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%
    16
    +0.14
    0.8%
    49
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    49
    +0.14
    0.01
    16
    +0.14
    0.01
    255
    +0.13
    0.01
    Negative Logits
    §
    -2.56
    ĨĴ
    -2.44
    Ĥ
    -2.33
    ĥ½
    -2.33
    Ĭ
    -2.33
    ĸ´
    -2.28
    İ
    -2.28
    Ĥ¬
    -2.20
    ı
    -2.19
    ¿
    -2.17
    POSITIVE LOGITS
    seud
    1.80
    gressive
    1.70
    ressor
    1.65
    ressive
    1.61
    ital
    1.58
    actor
    1.58
    gap
    1.55
    ulsion
    1.51
    iste
    1.51
    ived
    1.50
    Activations Density 0.005%

    No Known Activations