© 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. 4-RES-SM
    11. 10429
    Prev
    Next
    INDEX
    Explanations

    descriptions related to the performance and specifications of vehicles

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    173
    +0.12
    0.6%
    466
    +0.11
    0.6%
    89
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    173
    +0.12
    0.13
    62
    +0.11
    0.03
    208
    +0.10
    0.09
    Negative Logits
     gossip
    -1.79
     commune
    -1.73
     discourse
    -1.72
     cens
    -1.69
     migrants
    -1.69
     excretion
    -1.64
     feces
    -1.64
     activism
    -1.63
     menstru
    -1.62
     defe
    -1.61
    POSITIVE LOGITS
     warranty
    2.68
     chassis
    2.58
     upgraded
    2.54
     manufacturer
    2.50
     manufactured
    2.49
     accessories
    2.38
     BMW
    2.37
     manufacturers
    2.37
     upgrades
    2.32
     Chrysler
    2.29
    Activations Density 3.977%

    No Known Activations