© 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. Residuals
    9. 1-RES-SM
    11. 25805
    Prev
    Next
    INDEX
    Explanations

    phrases related to increases in quantities or thresholds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/1-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    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
    +0.16
    0.9%
    156
    +0.13
    0.7%
    23
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    414
    +0.16
    0.04
    327
    +0.13
    0.03
    11
    +0.13
    0.03
    Negative Logits
    ¿½
    -1.97
    ARY
    -1.89
    assa
    -1.83
    ridge
    -1.78
    ships
    -1.77
    liography
    -1.75
    ·¸
    -1.73
    thouse
    -1.71
    ĥ½
    -1.71
    sburg
    -1.69
    POSITIVE LOGITS
     radius
    1.81
     temporal
    1.64
     sensitivity
    1.64
     yield
    1.62
     detection
    1.62
     diameter
    1.59
     slope
    1.59
     velocity
    1.58
     quantification
    1.57
     amounts
    1.56
    Activations Density 0.086%

    No Known Activations