© 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. 27557
    Prev
    Next
    INDEX
    Explanations

    medical terms related to respiratory and musculoskeletal 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/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
    111
    +0.14
    0.8%
    13
    +0.12
    0.7%
    93
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    262
    +0.14
    0.02
    92
    +0.12
    0.01
    101
    +0.11
    0.01
    Negative Logits
     national
    -1.95
     ours
    -1.83
     mine
    -1.54
     conflicting
    -1.45
     nation
    -1.45
     sort
    -1.43
     hers
    -1.42
     hundred
    -1.41
     describe
    -1.39
     definite
    -1.38
    POSITIVE LOGITS
    imum
    1.61
    aic
    1.56
    £
    1.55
    gia
    1.55
    à±į
    1.54
    isms
    1.54
    scope
    1.48
    istic
    1.47
    ume
    1.46
    agna
    1.42
    Activations Density 0.087%

    No Known Activations