© 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. 1-RES-SM
    11. 28448
    Prev
    Next
    INDEX
    Explanations

    references to news articles and headlines

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    505
    +0.13
    0.7%
    201
    +0.12
    0.7%
    490
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    505
    +0.13
    0.03
    490
    +0.12
    0.02
    471
    +0.12
    0.02
    Negative Logits
    ĭ
    -3.39
    ĥ½
    -3.29
    IJ
    -3.12
    Īĺ
    -2.95
    §
    -2.94
    ¯
    -2.93
    Į
    -2.90
    ı
    -2.84
    ij
    -2.84
    ¤
    -2.81
    POSITIVE LOGITS
    ios
    2.26
    reader
    1.96
    table
    1.92
    flash
    1.92
     clips
    1.79
    stand
    1.78
    piece
    1.76
    card
    1.76
    letters
    1.74
    dro
    1.74
    Activations Density 0.103%

    No Known Activations