© 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. 10104
    Prev
    Next
    INDEX
    Explanations

    names of people, particularly with the surname "Nichols."

    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
    322
    +0.14
    0.8%
    173
    +0.11
    0.6%
    316
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.14
    0.05
    391
    +0.11
    0.07
    477
    +0.11
    0.05
    Negative Logits
     inches
    -1.78
    cycl
    -1.62
    rics
    -1.62
    ocument
    -1.55
    hemat
    -1.51
    etr
    -1.47
     case
    -1.47
    izations
    -1.45
    rient
    -1.45
    ximately
    -1.43
    POSITIVE LOGITS
    ©
    2.27
    µ
    2.09
    ŀ
    2.08
    ¸
    1.95
    ardo
    1.93
    ij
    1.85
    ¹
    1.84
    ª
    1.83
    Ĺ
    1.82
    ¡
    1.82
    Activations Density 0.565%

    No Known Activations