© 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. 2-RES-SM
    11. 27181
    Prev
    Next
    INDEX
    Explanations

    quantitative data related to patients and their medical conditions

    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
    408
    +0.13
    0.7%
    21
    +0.12
    0.7%
    311
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    163
    +0.13
    0.02
    184
    +0.12
    0.03
    186
    +0.12
    0.03
    Negative Logits
     trademarks
    -1.45
    ogy
    -1.44
    acetic
    -1.41
    nolimits
    -1.40
     bool
    -1.35
    rypt
    -1.34
    eration
    -1.34
    hbar
    -1.33
    upt
    -1.32
    ruz
    -1.32
    POSITIVE LOGITS
    ĻĤ
    2.13
    »¿
    1.85
     grouped
    1.82
    ²
    1.71
     selected
    1.69
    ·¸
    1.64
     sequentially
    1.52
    OPLE
    1.50
     individually
    1.49
     chosen
    1.46
    Activations Density 0.220%

    No Known Activations