© 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. 13729
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    424
    +0.12
    0.7%
    500
    +0.12
    0.7%
    240
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    0
    -0.12
    0.00
    1
    -0.12
    0.00
    2
    -0.12
    0.00
    Negative Logits
    »
    -2.43
    ļ
    -2.35
    ²
    -2.24
    ĸ
    -2.08
    ½
    -1.99
    ³
    -1.96
    ķ
    -1.95
    ŀ
    -1.91
    ĥ½
    -1.90
    Ĥ¬
    -1.86
    POSITIVE LOGITS
    elves
    1.84
    hors
    1.61
    zu
    1.61
    icals
    1.57
    heimer
    1.55
    uits
    1.53
    оваÑĤÑĮ
    1.52
     gods
    1.49
    ὶ
    1.48
    uous
    1.47
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.