© 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. 29430
    Prev
    Next
    INDEX
    Explanations

    terms related to community and communal activities

    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
    111
    +0.16
    0.9%
    410
    +0.14
    0.8%
    443
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.16
    0.03
    285
    +0.14
    0.02
    17
    +0.13
    0.01
    Negative Logits
    IJ
    -2.02
    »
    -2.01
    ľĵ
    -2.00
    į
    -1.92
    ij
    -1.91
      ↵
    -1.90
    ļ
    -1.89
    -1.89
    č↵
    -1.89
    -1.89
    POSITIVE LOGITS
    ittal
    1.91
    azine
    1.80
    urious
    1.72
    anche
    1.72
    RUPT
    1.68
    wick
    1.62
    anches
    1.61
    ISS
    1.60
    utor
    1.58
    unction
    1.58
    Activations Density 0.166%

    No Known Activations