© 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. 24625
    Prev
    Next
    INDEX
    Explanations

    instances of the word "of" and related phrases, indicating a focus on possession 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
    23
    +0.32
    1.9%
    478
    +0.17
    1.0%
    156
    +0.17
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    330
    +0.32
    0.04
    457
    +0.17
    0.05
    69
    +0.17
    0.05
    Negative Logits
    /~
    -1.81
    /@
    -1.81
    fal
    -1.78
     Arena
    -1.74
    holder
    -1.72
     behind
    -1.60
     µL
    -1.59
    ruptcy
    -1.57
    /.
    -1.54
     premie
    -1.52
    POSITIVE LOGITS
    ĻĤ
    2.45
     how
    1.77
    ľĵ
    1.72
    ¿½
    1.63
    them
    1.62
    him
    1.59
    itely
    1.56
     what
    1.56
    ...](
    1.52
     our
    1.51
    Activations Density 0.348%

    No Known Activations