© 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. 25655
    Prev
    Next
    INDEX
    Explanations

    medical and pharmaceutical terms related to immunology and treatment protocols

    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
    +0.15
    0.8%
    47
    +0.14
    0.8%
    440
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    440
    +0.15
    0.03
    134
    +0.14
    0.03
    439
    +0.12
    0.02
    Negative Logits
     homeless
    -1.78
     yours
    -1.74
     eternity
    -1.71
     Flying
    -1.67
     Else
    -1.66
     busy
    -1.65
     tourists
    -1.64
     lonely
    -1.64
     happier
    -1.62
     else
    -1.61
    POSITIVE LOGITS
    umab
    2.09
     oxidase
    2.05
    eral
    2.02
    acker
    1.90
    receptor
    1.89
     reductase
    1.85
    blower
    1.77
    ungs
    1.70
     suppressor
    1.67
    azole
    1.67
    Activations Density 0.210%

    No Known Activations