© 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. 1-RES-SM
    11. 29027
    Prev
    Next
    INDEX
    Explanations

    declarations of variables or parameters in programming 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
    2
    +0.14
    0.8%
    444
    +0.14
    0.8%
    35
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    35
    +0.14
    0.01
    142
    +0.14
    0.02
    444
    +0.13
    0.02
    Negative Logits
    tti
    -1.59
    matic
    -1.58
    hip
    -1.56
    ktiv
    -1.53
    OLOG
    -1.51
     else
    -1.46
    paces
    -1.42
    ATES
    -1.41
    asmod
    -1.37
    cology
    -1.37
    POSITIVE LOGITS
    ennial
    1.79
    ipher
    1.66
    endant
    1.62
    leys
    1.61
    rypted
    1.59
     measure
    1.58
    endants
    1.57
    eleration
    1.55
    ieux
    1.50
    annon
    1.50
    Activations Density 0.039%

    No Known Activations