© 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. 24192
    Prev
    Next
    INDEX
    Explanations

    patterns of numerical data

    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
    53
    +0.21
    1.4%
    23
    +0.16
    1.0%
    478
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.21
    0.18
    17
    +0.16
    0.06
    431
    +0.11
    0.08
    Negative Logits
     (“
    -1.69
    ĸ
    -1.56
    cript
    -1.52
     primer
    -1.48
    ł
    -1.42
     references
    -1.37
    orial
    -1.37
     measures
    -1.36
    emat
    -1.33
     Game
    -1.32
    POSITIVE LOGITS
    ––––––––
    1.74
    dered
    1.71
    ================================================
    1.63
    =======================
    1.60
    ===========================
    1.60
    possible
    1.59
    rceil
    1.58
    ----------------------------------------------------
    1.58
    founded
    1.57
    =================================
    1.57
    Activations Density 1.162%

    No Known Activations