© 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 EvalsExportsAPI 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. 30423
    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
    252
    +0.14
    0.8%
    465
    +0.13
    0.7%
    235
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    0
    -0.14
    0.00
    1
    -0.13
    0.00
    2
    -0.12
    0.00
    Negative Logits
    borough
    -1.59
    ujah
    -1.51
    ocese
    -1.47
     apologize
    -1.46
    ²
    -1.46
    andez
    -1.42
    acles
    -1.41
     Gabriel
    -1.39
    chor
    -1.39
    ала
    -1.36
    POSITIVE LOGITS
     consideration
    1.61
     minds
    1.47
     clarification
    1.44
     mins
    1.44
     us
    1.36
    mable
    1.36
    Seconds
    1.35
     appearances
    1.33
     compatibility
    1.32
     recogn
    1.31
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.