© 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. 4-RES-SM
    11. 9133
    Prev
    Next
    INDEX
    Explanations

    references to the word "Fab" or variations of it, indicating a focus on something related to the term that signifies excellent or fabulous qualities

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    21
    +0.17
    1.0%
    443
    +0.17
    0.9%
    300
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.17
    0.03
    443
    +0.17
    0.03
    386
    +0.13
    0.01
    Negative Logits
    izing
    -1.75
     times
    -1.63
    places
    -1.61
     time
    -1.60
    ational
    -1.58
    laid
    -1.58
     point
    -1.57
     questions
    -1.55
     place
    -1.51
     clubs
    -1.39
    POSITIVE LOGITS
    ulous
    2.62
    ulously
    2.56
    ric
    2.27
    ruary
    2.26
    rice
    2.26
    rique
    2.15
    io
    2.14
    erge
    2.13
    aceae
    2.09
    ian
    2.08
    Activations Density 0.229%

    No Known Activations