© 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. 31982
    Prev
    Next
    INDEX
    Explanations

    phrases related to competitive gaming dynamics

    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
    342
    +0.19
    1.1%
    161
    +0.12
    0.7%
    277
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    4
    +0.19
    0.39
    156
    +0.12
    0.39
    428
    +0.11
    0.31
    Negative Logits
    EventArgs
    -1.68
    ĥ½
    -1.66
    ĻĤ
    -1.58
    £
    -1.57
    Īĺ
    -1.55
    blockList
    -1.54
    ![(
    -1.48
    ognition
    -1.45
    mapsto
    -1.45
    úblic
    -1.45
    POSITIVE LOGITS
     sail
    1.56
     minister
    1.48
    ]{.
    1.47
     sailing
    1.44
     Cruise
    1.38
     graduating
    1.33
     agency
    1.29
    eu
    1.28
    ](
    1.27
     Ãī
    1.26
    Activations Density 5.012%

    No Known Activations