© 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 EvalsExportsAPI 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. 30452
    Prev
    Next
    INDEX
    Explanations

    specific data parameters or attributes related to computer programming or coding practices

    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
    186
    +0.27
    1.6%
    419
    +0.14
    0.8%
    198
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.27
    0.06
    483
    +0.14
    0.16
    476
    +0.13
    0.18
    Negative Logits
    ¤
    -1.59
    ¥
    -1.54
    igation
    -1.49
    £
    -1.48
    ©
    -1.39
    ij
    -1.38
    "}](#
    -1.37
    ités
    -1.35
    ¼
    -1.35
    poons
    -1.33
    POSITIVE LOGITS
     alike
    1.89
    %.
    1.69
     worth
    1.63
     respectively
    1.57
    ~.
    1.51
     alone
    1.50
    .[]{
    1.48
    .).
    1.44
     collectively
    1.43
     _(
    1.40
    Activations Density 7.875%

    No Known Activations