© 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. 31899
    Prev
    Next
    INDEX
    Explanations

    phrases related to operational management and control systems

    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
    79
    +0.14
    0.8%
    468
    +0.13
    0.7%
    461
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.14
    0.03
    79
    +0.13
    0.02
    461
    +0.12
    0.03
    Negative Logits
    ĻĤ
    -2.31
    ¨
    -2.03
    ¯
    -1.90
    ĥ½
    -1.85
    chez
    -1.83
    »¿
    -1.82
    ľĵ
    -1.81
    GREEK
    -1.77
    tgz
    -1.72
    ©
    -1.71
    POSITIVE LOGITS
     mechanisms
    2.21
     parameters
    2.18
     mechanism
    2.11
     variables
    1.91
     panel
    1.91
     applicability
    1.90
    osen
    1.88
    isp
    1.80
     panels
    1.79
    acting
    1.75
    Activations Density 0.138%

    No Known Activations