© 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. 29666
    Prev
    Next
    INDEX
    Explanations

    numerical values related to products and their specifications

    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
    156
    +0.14
    0.8%
    278
    +0.12
    0.7%
    152
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.14
    0.17
    271
    +0.12
    0.04
    17
    +0.11
    0.07
    Negative Logits
    ostatic
    -1.82
    puted
    -1.35
    constant
    -1.33
    othermal
    -1.31
    consuming
    -1.29
     deepest
    -1.29
    rogens
    -1.26
     inverse
    -1.25
    having
    -1.25
     CONTRIBUTORS
    -1.25
    POSITIVE LOGITS
     onwards
    1.63
     —
    1.62
    ÅĽÄĩ
    1.61
    ères
    1.57
    tracks
    1.55
    cias
    1.52
    umi
    1.50
     (“
    1.49
    .“
    1.46
    essages
    1.45
    Activations Density 0.866%

    No Known Activations