© 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. 9829
    Prev
    Next
    INDEX
    Explanations

    names and titles related to individuals in the entertainment or political sectors

    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
    500
    +0.13
    0.7%
    88
    +0.13
    0.7%
    478
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    369
    +0.13
    0.06
    410
    +0.13
    0.06
    98
    +0.12
    0.02
    Negative Logits
     WARRANTY
    -1.58
     @@
    -1.40
    nsylvania
    -1.34
    ivities
    -1.33
     Connecticut
    -1.31
     remod
    -1.29
    /-/
    -1.29
    itudes
    -1.28
     interest
    -1.27
    ometers
    -1.27
    POSITIVE LOGITS
    Į
    4.04
    ī
    3.88
    «
    3.84
    ½
    3.79
    Ī
    3.77
    ĩ
    3.74
    ¤
    3.71
    ĥ
    3.62
    ´
    3.61
    Ń
    3.60
    Activations Density 0.571%

    No Known Activations