© 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. 13266
    Prev
    Next
    INDEX
    Explanations

    elements related to financial metrics or statistics

    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
    121
    +0.24
    1.4%
    161
    +0.16
    0.9%
    23
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    121
    +0.24
    0.14
    23
    +0.16
    0.19
    36
    +0.14
    0.17
    Negative Logits
     Dell
    -1.55
     Williamson
    -1.51
    mortem
    -1.50
    ologist
    -1.48
     Edison
    -1.40
    ktop
    -1.39
     Anderson
    -1.38
     Silva
    -1.37
     Goldman
    -1.37
     Bras
    -1.37
    POSITIVE LOGITS
    $]{}
    1.71
    ](
    1.66
    $.[]{
    1.55
    .**]{}
    1.52
    {}{
    1.51
    |$.
    1.51
     ]{}
    1.50
    hib
    1.50
    |_{
    1.49
    '$.
    1.48
    Activations Density 4.762%

    No Known Activations