© 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. 26506
    Prev
    Next
    INDEX
    Explanations

    medical terms and conditions related to surgeries and treatments

    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
    369
    +0.17
    1.0%
    156
    +0.15
    0.9%
    501
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.17
    -0.08
    152
    +0.15
    0.11
    23
    +0.13
    0.15
    Negative Logits
    quo
    -1.65
    ย
    -1.54
    acular
    -1.48
    inent
    -1.43
    Ïīν
    -1.41
    amente
    -1.39
    обÑĭ
    -1.37
    ล
    -1.31
    iously
    -1.29
    ี
    -1.29
    POSITIVE LOGITS
    ======
    1.73
     expects
    1.64
     need
    1.62
     cheaper
    1.48
     advantage
    1.46
     needed
    1.36
     wont
    1.34
     via
    1.33
     misses
    1.33
     footing
    1.31
    Activations Density 5.778%

    No Known Activations