© 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. 1-RES-SM
    11. 26223
    Prev
    Next
    INDEX
    Explanations

    references to display or visual presentation elements

    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
    473
    +0.16
    0.9%
    156
    +0.15
    0.9%
    255
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    473
    +0.16
    0.03
    392
    +0.15
    0.02
    408
    +0.12
    0.02
    Negative Logits
    iedad
    -1.70
    woke
    -1.62
    wered
    -1.46
    hom
    -1.44
    §
    -1.43
    ureus
    -1.42
    idelberg
    -1.42
    aeda
    -1.41
    fasterxml
    -1.40
     extinct
    -1.39
    POSITIVE LOGITS
    manship
    1.95
    nail
    1.88
    eners
    1.71
    ership
    1.69
     sight
    1.56
    encies
    1.56
    lish
    1.54
    ening
    1.53
    urized
    1.51
     senses
    1.50
    Activations Density 0.073%

    No Known Activations