© 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. 14360
    Prev
    Next
    INDEX
    Explanations

    events related to sports and competitions

    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
    156
    +0.29
    1.8%
    21
    +0.25
    1.5%
    56
    +0.14
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.29
    0.04
    80
    +0.25
    0.01
    21
    +0.14
    0.02
    Negative Logits
    ī
    -3.51
    -3.45
    ↵↵
    -3.45
    ↵
    -3.45
    ↵↵
    -3.45
    ↵
    -3.45
    ↵↵
    -3.45
    -3.45
    ↵
    -3.45
    -3.45
    POSITIVE LOGITS
     learnt
    1.92
     ‘
    1.91
     padd
    1.87
     crew
    1.86
     finishing
    1.85
     travelled
    1.84
     camping
    1.84
     favourite
    1.80
     Crew
    1.78
     attendance
    1.74
    Activations Density 4.002%

    No Known Activations