© 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. 31951
    Prev
    Next
    INDEX
    Explanations

    phrases and patterns related to collaboration and teamwork

    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
    478
    +0.17
    1.0%
    496
    +0.12
    0.7%
    494
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    494
    +0.17
    0.07
    402
    +0.12
    0.06
    496
    +0.11
    0.07
    Negative Logits
    []{
    -1.62
    olerance
    -1.49
    ’
    -1.47
    buffer
    -1.44
    hex
    -1.41
    TeX
    -1.41
    load
    -1.41
     tolerance
    -1.41
    felt
    -1.39
    ibus
    -1.39
    POSITIVE LOGITS
    ı
    2.26
     vice
    2.22
    Ķ
    2.12
    Ī
    2.08
    İ
    2.00
    ĨĴ
    2.00
    Ŀ
    1.88
    ®
    1.88
    §
    1.87
    Ļª
    1.82
    Activations Density 0.535%

    No Known Activations