© 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. 27468
    Prev
    Next
    INDEX
    Explanations

    terms related to growth or increase in various contexts

    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
    156
    +0.17
    0.9%
    23
    +0.14
    0.7%
    376
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    327
    +0.17
    0.03
    414
    +0.14
    0.03
    370
    +0.12
    0.03
    Negative Logits
    lio
    -1.93
    lotte
    -1.82
    olini
    -1.79
    chen
    -1.77
    ksen
    -1.73
    kets
    -1.72
    thouse
    -1.68
    ader
    -1.64
    ilda
    -1.63
    ician
    -1.63
    POSITIVE LOGITS
     BSD
    1.69
     visibility
    1.56
    plify
    1.54
     magnitude
    1.50
     sensitivity
    1.47
     usefulness
    1.46
     halfway
    1.44
     individuals
    1.41
     quantification
    1.41
     heights
    1.41
    Activations Density 0.120%

    No Known Activations