© 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. 28150
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate opinions or perspectives

    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
    48
    +0.12
    0.6%
    441
    +0.11
    0.6%
    347
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    54
    +0.12
    0.00
    314
    +0.11
    0.00
    294
    +0.11
    0.00
    Negative Logits
    ¡
    -2.80
    Īĺ
    -2.79
    ľĵ
    -2.76
    Ģ
    -2.65
    ¸
    -2.62
    ²
    -2.55
    ŀ
    -2.48
    ľ
    -2.47
    ł
    -2.40
    ±
    -2.33
    POSITIVE LOGITS
    MAX
    1.49
    nikov
    1.45
    aret
    1.45
    ondo
    1.44
    eker
    1.44
    photon
    1.43
    ashing
    1.42
    emit
    1.40
    ucci
    1.39
    OMA
    1.37
    Activations Density 0.000%

    No Known Activations