© 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. 31533
    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
    56
    +0.15
    0.9%
    373
    +0.13
    0.7%
    252
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    0
    -0.15
    0.00
    1
    -0.13
    0.00
    2
    -0.12
    0.00
    Negative Logits
    ª
    -1.81
    Į
    -1.80
    Ń
    -1.61
    ores
    -1.55
    ĸ
    -1.51
     коÑĤоÑĢ
    -1.50
    ³
    -1.49
     envelope
    -1.48
    ©
    -1.47
    Ĩ
    -1.47
    POSITIVE LOGITS
    nier
    1.57
    mium
    1.56
    afood
    1.52
    ners
    1.46
     hydrochlor
    1.45
     biomarkers
    1.43
    TOF
    1.43
    ferent
    1.43
    ytics
    1.42
    \$
    1.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.