© 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. 12678
    Prev
    Next
    INDEX
    Explanations

    quantitative measurements related to medical and physiological parameters

    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
    21
    +0.26
    1.5%
    255
    +0.13
    0.8%
    92
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    92
    +0.26
    0.02
    245
    +0.13
    0.02
    203
    +0.12
    0.03
    Negative Logits
     follow
    -1.62
     successive
    -1.60
    Å¡ÃŃ
    -1.51
    quel
    -1.50
    terest
    -1.50
     implement
    -1.47
    essen
    -1.47
    ward
    -1.46
     diagrams
    -1.46
    ités
    -1.41
    POSITIVE LOGITS
    000001
    1.98
    ĺ
    1.87
    ©
    1.86
    005
    1.77
    025
    1.74
    0025
    1.73
    Ĵ
    1.71
    001
    1.67
    05
    1.65
    0001
    1.64
    Activations Density 0.154%

    No Known Activations