© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 28877
    Prev
    Next
    INDEX
    Explanations

    the word "carries"

    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
    376
    +0.21
    1.2%
    114
    +0.12
    0.7%
    474
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    114
    +0.21
    0.01
    359
    +0.12
    0.01
    381
    +0.12
    0.01
    Negative Logits
    ems
    -1.77
    ices
    -1.67
    lew
    -1.50
    lein
    -1.46
    s
    -1.44
    owl
    -1.44
    sson
    -1.44
     orbits
    -1.39
    illes
    -1.39
    ros
    -1.38
    POSITIVE LOGITS
    ¢
    1.95
     forward
    1.89
    Īĺ
    1.87
    ource
    1.78
    Ģ
    1.74
     away
    1.66
    chitz
    1.63
    chool
    1.63
    mith
    1.62
    ¤
    1.60
    Activations Density 0.015%

    No Known Activations