© 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. 28886
    Prev
    Next
    INDEX
    Explanations

    references to mass or mass-related concepts

    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
    0.8%
    266
    +0.13
    0.7%
    299
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    266
    +0.15
    0.02
    426
    +0.13
    0.02
    291
    +0.12
    0.02
    Negative Logits
    lı
    -1.73
    ften
    -1.65
    ses
    -1.60
    scriptions
    -1.59
    las
    -1.55
    rapeut
    -1.50
    sis
    -1.49
     say
    -1.49
    iances
    -1.48
    ÑĢÑĥг
    -1.47
    POSITIVE LOGITS
    achusetts
    2.86
     spectrometry
    1.95
    Ļª
    1.78
    ARRAY
    1.74
     ordinance
    1.69
    ceral
    1.69
    "}](#
    1.65
    ¤
    1.64
    gap
    1.57
    ĺ
    1.46
    Activations Density 0.009%

    No Known Activations