© 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. 1-RES-SM
    11. 27928
    Prev
    Next
    INDEX
    Explanations

    references to children and their needs in various contexts

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    201
    +0.15
    0.8%
    498
    +0.14
    0.8%
    17
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    51
    +0.15
    0.04
    128
    +0.14
    0.05
    222
    +0.13
    0.05
    Negative Logits
    PLC
    -1.79
     compromise
    -1.65
     pipelines
    -1.62
    INCLUDING
    -1.56
     brute
    -1.53
     solvent
    -1.50
    WHM
    -1.47
     merchants
    -1.47
     Terror
    -1.47
     else
    -1.46
    POSITIVE LOGITS
    Ĭ
    2.48
    thood
    1.94
    children
    1.84
    ĸ´
    1.76
    ħ
    1.76
    ilda
    1.75
    arean
    1.73
    ĭ
    1.73
     infant
    1.71
    natal
    1.70
    Activations Density 1.489%

    No Known Activations