© 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. 26219
    Prev
    Next
    INDEX
    Explanations

    terms related to pelvic health and anatomy

    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
    156
    +0.16
    1.0%
    71
    +0.14
    0.8%
    128
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.16
    0.01
    502
    +0.14
    0.01
    362
    +0.13
    0.01
    Negative Logits
     yours
    -2.02
     mine
    -1.57
     bipartisan
    -1.56
     sudden
    -1.56
     trusting
    -1.54
     suspicion
    -1.53
     regret
    -1.52
     perfect
    -1.50
     theirs
    -1.49
     pure
    -1.48
    POSITIVE LOGITS
    "}](#
    2.22
    gia
    1.90
    nik
    1.77
    wort
    1.70
    dan
    1.67
    leen
    1.63
    tip
    1.62
    iom
    1.60
    fonts
    1.58
    à±į
    1.57
    Activations Density 0.054%

    No Known Activations