© 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. 30914
    Prev
    Next
    INDEX
    Explanations

    terms related to attention deficit hyperactivity disorder (ADHD) and its effects on behavior and performance

    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
    47
    +0.16
    0.9%
    436
    +0.14
    0.8%
    35
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    123
    +0.16
    0.12
    35
    +0.14
    0.02
    246
    +0.12
    0.13
    Negative Logits
    cember
    -1.93
     dividend
    -1.90
     bankruptcy
    -1.77
     affordable
    -1.77
     certification
    -1.72
     insider
    -1.70
     finance
    -1.69
    Cert
    -1.69
     coronavirus
    -1.66
     financing
    -1.65
    POSITIVE LOGITS
    ĻĤ
    3.47
    č↵
    3.31
    <|outofrange|>
    3.31
    3.31
    ↵  ³³³
    3.31
    3.31
    ↵
    3.31
    ↵
    3.31
    ↵
    3.31
    ↵
    3.31
    Activations Density 3.451%

    No Known Activations