© 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. 29162
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    267
    +0.16
    0.9%
    143
    +0.15
    0.9%
    285
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    0
    -0.16
    0.00
    1
    -0.15
    0.00
    2
    -0.14
    0.00
    Negative Logits
    hips
    -1.49
    nae
    -1.48
    eeper
    -1.38
    ropic
    -1.36
    wen
    -1.34
    arian
    -1.32
    DNA
    -1.32
     excised
    -1.31
    acht
    -1.29
    meal
    -1.29
    POSITIVE LOGITS
    aeda
    1.53
    fecture
    1.47
    inux
    1.42
    |=
    1.41
    "}](#
    1.39
    |
    1.38
    "|
    1.34
    =&
    1.33
    :%
    1.33
    TestCase
    1.32
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.