© 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. 12835
    Prev
    Next
    INDEX
    Explanations

    terms related to medical research and conditions involving cancer and treatment methodologies

    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
    419
    +0.16
    0.9%
    23
    +0.13
    0.7%
    369
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    419
    +0.16
    0.08
    361
    +0.13
    0.08
    134
    +0.11
    0.07
    Negative Logits
    Ļª
    -4.28
    º
    -3.89
    ¸
    -3.86
    ¼
    -3.85
    ļ
    -3.74
    ĥ½
    -3.65
    ¹
    -3.60
    Ŀ
    -3.57
    ĨĴ
    -3.57
    ĻĤ
    -3.54
    POSITIVE LOGITS
    ously
    1.73
     Experiments
    1.69
    ually
    1.69
     Results
    1.65
     Methods
    1.64
    ingly
    1.62
     Representative
    1.57
     further
    1.56
     Studies
    1.56
     First
    1.53
    Activations Density 0.756%

    No Known Activations