© 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. 2-RES-SM
    11. 28572
    Prev
    Next
    INDEX
    Explanations

    musical terminology and references to Polish musical traditions

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    204
    +0.16
    0.9%
    169
    +0.13
    0.8%
    153
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    33
    +0.16
    0.16
    204
    +0.13
    0.15
    362
    +0.11
    0.15
    Negative Logits
    "?"
    -1.73
     Verizon
    -1.67
     TX
    -1.61
     Sprint
    -1.56
     shutdown
    -1.55
     ourselves
    -1.48
     Obamacare
    -1.48
    igation
    -1.46
    driver
    -1.43
     Storage
    -1.42
    POSITIVE LOGITS
     accession
    1.74
     exile
    1.72
     splend
    1.68
    ).[
    1.66
     arist
    1.61
     Persian
    1.61
     fame
    1.59
     artistic
    1.58
     keen
    1.57
     bourgeois
    1.57
    Activations Density 4.564%

    No Known Activations