© 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. Residuals
    9. 1-RES-SM
    11. 29680
    Prev
    Next
    INDEX
    Explanations

    mathematical operations represented by symbols

    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
    478
    +0.17
    0.9%
    29
    +0.13
    0.7%
    94
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    472
    +0.17
    0.04
    94
    +0.13
    0.04
    340
    +0.12
    0.04
    Negative Logits
    iley
    -1.80
    ubert
    -1.57
    ises
    -1.46
    oder
    -1.46
    ulic
    -1.43
    NAL
    -1.42
    EMENT
    -1.42
    oster
    -1.41
    osp
    -1.41
    ritz
    -1.39
    POSITIVE LOGITS
    /âĪĴ
    2.21
    Ķ
    1.78
     skew
    1.57
    itarian
    1.56
    ī
    1.54
     jeans
    1.51
    Ĭ
    1.51
    quot
    1.50
    itary
    1.44
     hurry
    1.43
    Activations Density 0.223%

    No Known Activations