© 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. 2-RES-SM
    11. 10651
    Prev
    Next
    INDEX
    Explanations

    references to the South, particularly South Africa

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    +0.15
    0.9%
    362
    +0.14
    0.8%
    369
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    38
    +0.15
    0.03
    77
    +0.14
    0.02
    59
    +0.14
    0.02
    Negative Logits
    ĥ½
    -2.42
    ĩ
    -1.88
    ľĵ
    -1.81
    nlm
    -1.73
    ĻĤ
    -1.72
    doibase
    -1.65
    estion
    -1.64
    Į
    -1.62
    acity
    -1.60
    odic
    -1.59
    POSITIVE LOGITS
    cliffe
    2.29
    wick
    2.13
    ampton
    1.99
    umberland
    1.80
    field
    1.80
    western
    1.78
    wall
    1.73
    orne
    1.71
    pole
    1.68
    side
    1.63
    Activations Density 0.094%

    No Known Activations