© 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. 2-RES-SM
    11. 26925
    Prev
    Next
    INDEX
    Explanations

    terms related to the gastrointestinal and nervous systems

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    93
    +0.14
    0.8%
    498
    +0.11
    0.7%
    68
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.14
    -0.00
    68
    +0.11
    0.03
    8
    +0.11
    0.02
    Negative Logits
     appeal
    -1.90
     promise
    -1.90
     Parenthood
    -1.89
     sale
    -1.86
     sure
    -1.83
     price
    -1.79
     new
    -1.69
     harmless
    -1.67
     welcome
    -1.66
    blogger
    -1.61
    POSITIVE LOGITS
     composed
    1.92
    resis
    1.87
    icity
    1.83
    enberg
    1.77
     termed
    1.75
    ipel
    1.72
    encephal
    1.69
    vation
    1.68
     surrounded
    1.66
     protr
    1.66
    Activations Density 0.207%

    No Known Activations