© 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. 25048
    Prev
    Next
    INDEX
    Explanations

    references to the concept of belonging or community related to experiences

    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
    98
    +0.33
    2.2%
    478
    +0.23
    1.5%
    23
    +0.23
    1.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.33
    0.16
    98
    +0.23
    0.04
    291
    +0.23
    0.11
    Negative Logits
    "}](#
    -2.27
     weddings
    -1.61
     contender
    -1.54
    ival
    -1.36
     aliqu
    -1.34
    Sov
    -1.32
    chunk
    -1.31
    iNdEx
    -1.31
    "</
    -1.30
     encounters
    -1.29
    POSITIVE LOGITS
     same
    2.65
     latter
    2.38
    rapeut
    2.28
    rapeutics
    2.09
     aforementioned
    2.04
     sexes
    1.98
    same
    1.97
     usual
    1.95
     entire
    1.94
     thousands
    1.91
    Activations Density 1.738%

    No Known Activations