© 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. 29457
    Prev
    Next
    INDEX
    Explanations

    instances of the word "centers" or its variations in the text

    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
    +0.15
    0.9%
    144
    +0.12
    0.7%
    156
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.15
    0.01
    499
    +0.12
    0.01
    265
    +0.11
    0.01
    Negative Logits
    ellow
    -1.68
    ching
    -1.65
    athing
    -1.64
    ı
    -1.61
    §
    -1.60
     sudden
    -1.59
    gers
    -1.56
    ften
    -1.53
    ¿½
    -1.51
    ĻĤ
    -1.48
    POSITIVE LOGITS
    piece
    2.50
    pieces
    2.18
     pose
    1.89
    burg
    1.85
    pot
    1.82
    holder
    1.81
    er
    1.71
    ervation
    1.70
     fixture
    1.69
    imeter
    1.68
    Activations Density 0.018%

    No Known Activations