© 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. 27796
    Prev
    Next
    INDEX
    Explanations

    words that indicate temporal and conditional contexts

    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
    444
    +0.14
    0.8%
    21
    +0.12
    0.7%
    68
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    68
    +0.14
    0.07
    358
    +0.12
    0.07
    332
    +0.12
    0.04
    Negative Logits
    ĻĤ
    -4.12
    ¿½
    -3.71
    ŀ
    -3.49
    ĸ
    -3.39
    Ĵ
    -3.24
    ¾
    -3.20
    ¢
    -3.19
    ²
    -3.19
    ĨĴ
    -3.17
    Į
    -3.14
    POSITIVE LOGITS
    ^\[[@
    1.78
    ^(
    1.68
    [^
    1.68
    âĢ¡
    1.62
    âĢł
    1.55
    uate
    1.54
    forth
    1.51
    estyle
    1.46
    iture
    1.43
    vac
    1.43
    Activations Density 0.589%

    No Known Activations