© 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. 11525
    Prev
    Next
    INDEX
    Explanations

    terms related to medical procedures or 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/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
    78
    +0.22
    1.3%
    348
    +0.15
    0.9%
    136
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    502
    +0.22
    0.07
    136
    +0.15
    0.00
    93
    +0.13
    0.04
    Negative Logits
    mouth
    -1.97
    s
    -1.73
    tics
    -1.67
     beginning
    -1.58
    e
    -1.54
    er
    -1.54
    kin
    -1.49
    ing
    -1.49
    chitz
    -1.49
     only
    -1.48
    POSITIVE LOGITS
    1451450014514500
    2.14
    iox
    1.86
    ovember
    1.81
    aucoma
    1.80
    fefe
    1.77
    ublin
    1.76
    8
    1.76
    7
    1.75
    9
    1.70
    yla
    1.69
    Activations Density 0.264%

    No Known Activations