© 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. 26620
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "chart" and variations of it 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
    156
    +0.13
    0.8%
    139
    +0.11
    0.6%
    257
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    401
    +0.13
    0.01
    234
    +0.11
    0.01
    257
    +0.10
    0.01
    Negative Logits
    ĵ
    -1.90
    ¯
    -1.87
     tires
    -1.71
    §
    -1.68
     riders
    -1.61
    IJ
    -1.61
     miserable
    -1.59
    rivers
    -1.58
     precious
    -1.54
     await
    -1.51
    POSITIVE LOGITS
    oon
    2.17
    iary
    2.06
    istical
    1.99
    holder
    1.99
    esan
    1.80
    ball
    1.79
    imen
    1.73
    istics
    1.71
    doctoral
    1.69
    ete
    1.66
    Activations Density 0.014%

    No Known Activations