© 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. 28105
    Prev
    Next
    INDEX
    Explanations

    references to football and athletics

    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
    176
    +0.12
    0.7%
    111
    +0.11
    0.6%
    118
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.12
    0.05
    271
    +0.11
    0.01
    156
    +0.11
    0.03
    Negative Logits
     ich
    -1.74
     maternal
    -1.65
     hers
    -1.60
     taken
    -1.58
     pregnant
    -1.56
     remembering
    -1.56
     suppose
    -1.54
     pleading
    -1.53
     breastfeeding
    -1.53
     contacting
    -1.50
    POSITIVE LOGITS
     playoffs
    1.97
     Bundes
    1.93
     League
    1.91
    aña
    1.85
     Stadium
    1.81
    ILITY
    1.80
    scape
    1.77
     league
    1.75
    makers
    1.69
    League
    1.69
    Activations Density 0.205%

    No Known Activations