© 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 EvalsExportsinterp-engineNEWAPI 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. 26395
    Prev
    Next
    INDEX
    Explanations

    the word "gonna."

    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
    156
    +0.22
    1.3%
    376
    +0.18
    1.1%
    321
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    418
    +0.22
    0.01
    433
    +0.18
    0.01
    321
    +0.13
    0.01
    Negative Logits
    ¦
    -1.82
    ı
    -1.69
    inals
    -1.66
    ĥ½
    -1.61
    ´
    -1.55
    ser
    -1.54
    oin
    -1.51
     advertised
    -1.50
    ĩ
    -1.47
    ascular
    -1.46
    POSITIVE LOGITS
     decir
    1.55
    blems
    1.53
    vier
    1.51
    vable
    1.50
    vu
    1.46
    fail
    1.45
     torture
    1.42
    proj
    1.42
     combat
    1.39
    fu
    1.36
    Activations Density 0.029%

    No Known Activations