© 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. 14376
    Prev
    Next
    INDEX
    Explanations

    references to the term "Du."

    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
    31
    +0.17
    0.9%
    354
    +0.15
    0.8%
    21
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    31
    +0.17
    0.03
    354
    +0.15
    0.03
    314
    +0.13
    0.02
    Negative Logits
     around
    -1.86
     unbiased
    -1.54
    "}](#
    -1.50
    liest
    -1.47
     ahead
    -1.47
     broadly
    -1.47
    izumab
    -1.43
    around
    -1.42
    iast
    -1.42
    growth
    -1.40
    POSITIVE LOGITS
    odenal
    2.46
    plicate
    2.31
    plic
    2.10
    plications
    1.98
    cks
    1.95
    º
    1.87
    plicated
    1.81
    plication
    1.80
    oden
    1.79
    ples
    1.73
    Activations Density 0.098%

    No Known Activations