© 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. 31932
    Prev
    Next
    INDEX
    Explanations

    various programming languages and related technical concepts within the context of web development

    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
    72
    +0.14
    0.8%
    331
    +0.12
    0.7%
    312
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    72
    +0.14
    0.06
    312
    +0.12
    0.06
    231
    +0.12
    0.06
    Negative Logits
    »¿
    -3.15
    Ļª
    -2.87
    ĵ
    -2.73
    ĭ
    -2.62
    į
    -2.52
    ĥ½
    -2.51
    Ĺ
    -2.48
    IJ
    -2.43
    Ħ
    -2.41
    Į
    -2.37
    POSITIVE LOGITS
    buntu
    1.79
     Python
    1.78
     Chrome
    1.71
    framework
    1.69
     backend
    1.66
     Version
    1.64
    stringify
    1.64
    dll
    1.62
     (@
    1.58
    inux
    1.56
    Activations Density 1.111%

    No Known Activations