© 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. 31515
    Prev
    Next
    INDEX
    Explanations

    references to medical terminology 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/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
    161
    +0.14
    0.8%
    496
    +0.13
    0.7%
    156
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.14
    0.27
    156
    +0.13
    0.29
    71
    +0.10
    0.27
    Negative Logits
    )):
    -1.46
    ))=
    -1.45
    __.
    -1.44
    orphisms
    -1.37
    orphism
    -1.35
     specialization
    -1.29
    lications
    -1.27
     alcohol
    -1.27
    __,
    -1.26
    ools
    -1.25
    POSITIVE LOGITS
    Īĺ
    3.23
    Ī
    3.15
    ĺ
    2.79
    ı
    2.77
    Ĥ
    2.76
    ĥ
    2.72
    IJ
    2.70
    º
    2.69
    ¡
    2.67
    ¼
    2.66
    Activations Density 5.332%

    No Known Activations