© 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. 4-RES-SM
    11. 10698
    Prev
    Next
    INDEX
    Explanations

    references to specific tauopathies and their characteristics

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    78
    +0.21
    1.2%
    255
    +0.15
    0.8%
    136
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    136
    +0.21
    0.00
    219
    +0.15
    0.02
    78
    +0.14
    0.00
    Negative Logits
     ”
    -1.88
    .“
    -1.86
    ”,
    -1.73
    ”.
    -1.62
     “
    -1.54
    .";
    -1.51
    ”:
    -1.51
     ****
    -1.45
     solved
    -1.45
    âĢŁ
    -1.42
    POSITIVE LOGITS
    ŀ
    3.76
    Ĭ
    3.71
    »¿
    3.54
    İ
    3.48
    ĵ
    3.47
    Ķ
    3.42
    ½
    3.42
    ¾
    3.42
    ı
    3.38
    ĩ
    3.34
    Activations Density 0.052%

    No Known Activations