© 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. 4-RES-SM
    11. 10924
    Prev
    Next
    INDEX
    Explanations

    terms related to health conditions and medical diagnoses

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    306
    +0.26
    1.6%
    21
    +0.19
    1.2%
    313
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.26
    -0.02
    21
    +0.19
    0.02
    489
    +0.11
    0.03
    Negative Logits
    ly
    -1.69
    liest
    -1.56
    izations
    -1.55
    isation
    -1.54
    isations
    -1.47
    ish
    -1.47
    ising
    -1.46
     of
    -1.45
    ization
    -1.43
    ially
    -1.40
    POSITIVE LOGITS
    ĻĤ
    1.95
    ermo
    1.47
    atem
    1.41
    adr
    1.34
    abilities
    1.32
    e
    1.30
    ável
    1.30
    abil
    1.29
    ember
    1.27
    (".
    1.27
    Activations Density 0.730%

    No Known Activations