© 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 EvalsExportsAPI 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. 26595
    Prev
    Next
    INDEX
    Explanations

    numerical data or timestamps

    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
    221
    +0.14
    0.8%
    478
    +0.14
    0.8%
    198
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    26
    +0.14
    0.04
    384
    +0.14
    0.04
    221
    +0.13
    0.04
    Negative Logits
    os
    -1.48
    bill
    -1.42
    ologically
    -1.40
    pet
    -1.39
    à±ģ
    -1.38
     (%)
    -1.36
    à«ĩ
    -1.33
    axis
    -1.32
     numbers
    -1.32
    osh
    -1.31
    POSITIVE LOGITS
    »¿
    1.81
    ŀ
    1.72
    Ļª
    1.69
    aliana
    1.68
    Ĥ
    1.64
    ¢
    1.61
    Ĵ
    1.55
    ı
    1.50
    ĥ½
    1.49
    leans
    1.48
    Activations Density 0.184%

    No Known Activations