© 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. 2-RES-SM
    11. 31358
    Prev
    Next
    INDEX
    Explanations

    specific medical and statistical data related to health

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    153
    +0.17
    1.0%
    24
    +0.15
    0.9%
    122
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    153
    +0.17
    0.06
    122
    +0.15
    0.06
    103
    +0.14
    0.07
    Negative Logits
     survives
    -1.56
    entric
    -1.52
     entit
    -1.50
    ){#
    -1.39
    matically
    -1.35
    [{
    -1.34
    reements
    -1.31
     deserve
    -1.29
    iary
    -1.28
     survived
    -1.28
    POSITIVE LOGITS
    ı
    1.33
    áĢº
    1.33
    inger
    1.29
    aco
    1.28
    isco
    1.27
    ~:
    1.27
     industries
    1.24
    ¸
    1.23
     tens
    1.23
    anges
    1.23
    Activations Density 2.599%

    No Known Activations