© 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. 24284
    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
    468
    +0.15
    0.8%
    30
    +0.11
    0.6%
    181
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    0
    -0.15
    0.00
    1
    -0.11
    0.00
    2
    -0.10
    0.00
    Negative Logits
    :(
    -1.63
    inating
    -1.58
    aping
    -1.55
    romycin
    -1.52
    inai
    -1.50
    acic
    -1.48
    imar
    -1.44
    ple
    -1.41
    imal
    -1.40
    iast
    -1.40
    POSITIVE LOGITS
    exports
    1.44
     etc
    1.43
     CAG
    1.38
     noises
    1.37
     scenery
    1.31
    fiddle
    1.31
     shuffle
    1.29
    gest
    1.28
     PCB
    1.26
     layout
    1.26
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.