© 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. 25462
    Prev
    Next
    INDEX
    Explanations

    recurring mentions of "crane."

    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
    410
    +0.14
    0.8%
    132
    +0.12
    0.7%
    468
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.14
    0.02
    132
    +0.12
    0.02
    142
    +0.12
    0.02
    Negative Logits
    erville
    -1.80
     truth
    -1.79
     forthcoming
    -1.74
     survival
    -1.74
     future
    -1.69
     survive
    -1.56
     desired
    -1.54
    rapeut
    -1.54
     vez
    -1.49
    象
    -1.48
    POSITIVE LOGITS
    amped
    2.00
    annon
    1.86
    ème
    1.79
    assic
    1.66
     compared
    1.65
    ups
    1.63
    illon
    1.62
    amping
    1.59
    oupe
    1.59
    iso
    1.59
    Activations Density 0.135%

    No Known Activations