© 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. 2-RES-SM
    11. 13703
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    504
    +0.12
    0.7%
    365
    +0.11
    0.6%
    390
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    0
    -0.12
    0.00
    1
    -0.11
    0.00
    2
    -0.11
    0.00
    Negative Logits
    osine
    -1.62
     fit
    -1.44
    htra
    -1.44
    artifactId
    -1.38
    }_{{\
    -1.37
    OO
    -1.36
    anine
    -1.34
    _{{{\
    -1.31
     hypothesis
    -1.30
    appropri
    -1.27
    POSITIVE LOGITS
    endar
    1.66
    ĨĴ
    1.57
     benefit
    1.56
    ferent
    1.51
     relief
    1.47
    urs
    1.45
    men
    1.42
    guard
    1.37
     assistance
    1.35
     reversed
    1.34
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.