© 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. 10317
    Prev
    Next
    INDEX
    Explanations

    locations and movements related to people

    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
    306
    +0.17
    0.9%
    307
    +0.14
    0.8%
    266
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    155
    +0.17
    0.07
    266
    +0.14
    0.09
    57
    +0.13
    0.10
    Negative Logits
    +/
    -1.64
    ème
    -1.54
    plasty
    -1.48
    urnal
    -1.47
     kidding
    -1.45
    +-
    -1.44
    obuf
    -1.42
    /+
    -1.40
    !--
    -1.39
    CUSSION
    -1.39
    POSITIVE LOGITS
     Philadelphia
    2.52
     Washington
    2.50
     Pennsylvania
    2.50
     Michigan
    2.47
     Chicago
    2.41
     Alabama
    2.39
     Florida
    2.32
     Los
    2.31
     Louisiana
    2.30
     New
    2.29
    Activations Density 1.694%

    No Known Activations