© 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. 4-RES-SM
    11. 9159
    Prev
    Next
    INDEX
    Explanations

    keywords and structures related to AngularJS application configuration

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    343
    +0.12
    0.7%
    76
    +0.12
    0.6%
    336
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.12
    0.02
    365
    +0.12
    0.02
    94
    +0.11
    0.01
    Negative Logits
    YPT
    -1.79
     Hardy
    -1.76
     vampire
    -1.75
     Buff
    -1.74
     vamp
    -1.73
     wolves
    -1.71
     Vamp
    -1.67
     Edgar
    -1.67
    wolf
    -1.66
    TES
    -1.66
    POSITIVE LOGITS
     Angular
    3.99
     ng
    3.56
    angular
    3.21
     angular
    2.91
     NG
    2.68
     Ng
    2.65
    Ang
    2.53
    ng
    2.42
     directive
    2.41
    IJ
    2.33
    Activations Density 0.243%

    No Known Activations