© 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. 25570
    Prev
    Next
    INDEX
    Explanations

    the concept of belonging or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    98
    +0.17
    1.0%
    478
    +0.16
    0.9%
    69
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.17
    0.11
    295
    +0.16
    0.06
    119
    +0.15
    0.06
    Negative Logits
    shire
    -1.59
    [
    -1.51
    avier
    -1.47
    [:
    -1.46
    inations
    -1.43
    het
    -1.43
    iment
    -1.40
    (@
    -1.39
    iang
    -1.31
     nickname
    -1.29
    POSITIVE LOGITS
    fered
    1.88
    erce
    1.51
     others
    1.51
    ked
    1.50
     course
    1.48
    laid
    1.48
     ___,
    1.43
     ourselves
    1.43
    nai
    1.41
    ène
    1.41
    Activations Density 0.731%

    No Known Activations