© 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. 26149
    Prev
    Next
    INDEX
    Explanations

    phrases indicating ownership or copyright claims

    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
    281
    +0.12
    0.7%
    194
    +0.11
    0.6%
    252
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    281
    +0.12
    0.03
    251
    +0.11
    0.03
    194
    +0.11
    0.03
    Negative Logits
    ¯
    -2.55
    Ŀ
    -2.50
    ŀ
    -2.40
    ¹
    -2.39
    ¡
    -2.33
    Ł
    -2.32
    ľĵ
    -2.29
    ¢
    -2.26
    ±
    -2.22
    ļ
    -2.19
    POSITIVE LOGITS
    usions
    1.90
    owing
    1.90
    ograft
    1.79
    iances
    1.72
     Things
    1.69
    igator
    1.67
    owed
    1.62
    ureus
    1.51
    erton
    1.51
     certificates
    1.48
    Activations Density 0.082%

    No Known Activations