© 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. 27817
    Prev
    Next
    INDEX
    Explanations

    descriptions of small towns and their characteristics

    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
    +0.14
    0.8%
    478
    +0.14
    0.8%
    507
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    436
    +0.14
    0.12
    321
    +0.14
    0.10
    98
    +0.12
    0.00
    Negative Logits
    isc
    -1.73
    aires
    -1.72
    zione
    -1.69
    liga
    -1.66
    iere
    -1.57
    à±į
    -1.56
    еÑģк
    -1.56
    lis
    -1.52
    orf
    -1.51
    aro
    -1.49
    POSITIVE LOGITS
     young
    1.92
     younger
    1.76
    iled
    1.73
     lot
    1.73
    unts
    1.71
    ĥ
    1.60
    ĸ
    1.60
    very
    1.56
    woke
    1.54
    iling
    1.53
    Activations Density 0.788%

    No Known Activations