© 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. 28185
    Prev
    Next
    INDEX
    Explanations

    locations and references to Los Angeles and its surrounding areas

    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
    156
    +0.20
    1.2%
    182
    +0.15
    0.9%
    111
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    182
    +0.20
    0.04
    71
    +0.15
    0.03
    160
    +0.13
    0.02
    Negative Logits
    ¸
    -1.85
    Ķ
    -1.79
    ¯
    -1.69
    ĥ½
    -1.68
    ±
    -1.65
    Īĺ
    -1.61
    rene
    -1.60
    ij
    -1.55
    ¦
    -1.55
    ĺ
    -1.54
    POSITIVE LOGITS
    à°¿
    1.91
    àµį
    1.88
    áĢ¸
    1.85
    illac
    1.80
    wagen
    1.78
    à±į
    1.73
     herself
    1.70
    ி
    1.69
    à±ģ
    1.68
    ual
    1.66
    Activations Density 0.086%

    No Known Activations