© 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. 26746
    Prev
    Next
    INDEX
    Explanations

    technical terms related to materials and processes in manufacturing or technology

    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
    +0.30
    1.8%
    2
    +0.13
    0.8%
    148
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    180
    +0.30
    0.01
    156
    +0.13
    0.01
    148
    +0.12
    0.01
    Negative Logits
    enson
    -1.54
     particular
    -1.54
    idegger
    -1.51
    olding
    -1.48
    atal
    -1.48
    elian
    -1.46
     deliberate
    -1.40
    heimer
    -1.35
    aying
    -1.33
    owing
    -1.33
    POSITIVE LOGITS
    à±į
    1.83
     sclerosis
    1.75
    àµį
    1.73
    naments
    1.70
    à«ĩ
    1.62
    pose
    1.56
    à±ģ
    1.51
    à°¿
    1.49
    bank
    1.47
    àµ
    1.43
    Activations Density 0.005%

    No Known Activations