© 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. 1-RES-SM
    11. 24205
    Prev
    Next
    INDEX
    Explanations

    terms related to immune response and antigens in medical contexts

    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
    +0.18
    1.1%
    219
    +0.12
    0.7%
    77
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.18
    0.03
    271
    +0.12
    0.01
    156
    +0.12
    0.02
    Negative Logits
    awed
    -1.70
    empre
    -1.66
     everything
    -1.66
    doing
    -1.61
     fprintf
    -1.60
     why
    -1.60
     }).
    -1.59
    obbsee
    -1.57
     what
    -1.55
     progress
    -1.54
    POSITIVE LOGITS
    avirus
    1.66
    arium
    1.64
    ics
    1.59
    optic
    1.59
    ic
    1.57
    vin
    1.57
    plate
    1.56
     receptor
    1.55
    ascus
    1.55
    etically
    1.54
    Activations Density 0.073%

    No Known Activations