© 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. 29078
    Prev
    Next
    INDEX
    Explanations

    references to sports terminology and statistics

    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
    410
    +0.14
    0.8%
    361
    +0.10
    0.5%
    423
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.14
    0.13
    369
    +0.10
    0.07
    129
    +0.10
    0.01
    Negative Logits
    ĻĤ
    -2.04
    visiae
    -1.79
    Ĥ
    -1.75
    .");
    -1.74
    Ļ
    -1.68
    â
    -1.65
     */,
    -1.59
    Īĺ
    -1.58
    ½
    -1.53
    )^[@
    -1.51
    POSITIVE LOGITS
    cast
    1.46
    ]:
    1.38
     conclusion
    1.36
     Stage
    1.32
     dilution
    1.31
     Division
    1.29
     loss
    1.29
     ‘
    1.27
     Count
    1.25
     lowered
    1.25
    Activations Density 2.736%

    No Known Activations