© 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. 2-RES-SM
    11. 10357
    Prev
    Next
    INDEX
    Explanations

    technical terms and programming constructs

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    489
    +0.15
    0.8%
    248
    +0.14
    0.8%
    407
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    407
    +0.15
    0.17
    455
    +0.14
    0.20
    404
    +0.14
    0.16
    Negative Logits
    ĻĤ
    -2.23
    ·¸
    -1.90
    ³
    -1.75
    ·
    -1.62
    ij
    -1.57
    ļ
    -1.57
    Ħ
    -1.56
    ¿½
    -1.56
    ²
    -1.56
    ľ
    -1.55
    POSITIVE LOGITS
    ör
    1.75
    ressor
    1.69
    blockList
    1.64
    fiddle
    1.61
    .\[
    1.56
    )",
    1.56
    ró
    1.55
    lei
    1.54
    oin
    1.51
    reon
    1.50
    Activations Density 7.540%

    No Known Activations