© 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 EvalsExportsinterp-engineNEWAPI 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. 24662
    Prev
    Next
    INDEX
    Explanations

    questions related to mathematical operations or properties

    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
    +0.27
    1.5%
    478
    +0.17
    0.9%
    356
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    108
    +0.27
    0.04
    48
    +0.17
    0.04
    356
    +0.13
    0.03
    Negative Logits
    ł
    -2.82
    Ŀ
    -2.78
    Ľ
    -2.68
    į
    -2.64
    §
    -2.61
    Ł
    -2.58
    ¡
    -2.57
    »
    -2.56
    ¥
    -2.56
    ·¸
    -2.54
    POSITIVE LOGITS
     ever
    1.66
    rael
    1.57
     upgrading
    1.54
     anybody
    1.52
     LORD
    1.49
     purchasing
    1.48
     smoke
    1.48
     buying
    1.46
     yours
    1.46
     spite
    1.45
    Activations Density 0.203%

    No Known Activations