© 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. 27858
    Prev
    Next
    INDEX
    Explanations

    references to Alzheimer's disease and related neurological 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
    321
    +0.15
    0.9%
    156
    +0.14
    0.8%
    290
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.15
    0.04
    156
    +0.14
    0.04
    111
    +0.13
    0.04
    Negative Logits
    érie
    -1.50
     unconditional
    -1.44
     outgoing
    -1.43
    allowed
    -1.41
     CIRCUIT
    -1.41
    lot
    -1.39
     fixing
    -1.39
     ballistic
    -1.39
    aid
    -1.39
    zos
    -1.38
    POSITIVE LOGITS
    genstein
    1.83
    umab
    1.69
     disease
    1.69
     diseases
    1.57
    osaurs
    1.55
    Äį
    1.53
     burden
    1.53
    zheimer
    1.52
    emia
    1.51
     activity
    1.51
    Activations Density 0.221%

    No Known Activations