© 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. 26923
    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
    296
    +0.13
    0.7%
    33
    +0.11
    0.6%
    24
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    0
    -0.13
    0.00
    1
    -0.11
    0.00
    2
    -0.10
    0.00
    Negative Logits
    ¾
    -1.88
    ³
    -1.84
    «
    -1.77
    Court
    -1.74
     Court
    -1.62
    ļ
    -1.59
    hood
    -1.56
    ½
    -1.54
    bery
    -1.52
    inally
    -1.50
    POSITIVE LOGITS
     ]$
    1.88
    .]{}
    1.72
    IPE
    1.65
     ):
    1.52
     [$
    1.45
     me
    1.45
     alone
    1.45
     ]{}
    1.43
    \]]{}
    1.42
    $_{
    1.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.