© 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 EvalsExportsAPI 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. 27428
    Prev
    Next
    INDEX
    Explanations

    technical jargon and code-related terms

    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
    508
    +0.14
    0.9%
    405
    +0.10
    0.6%
    47
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    508
    +0.14
    0.10
    348
    +0.10
    0.10
    386
    +0.10
    0.07
    Negative Logits
     wounded
    -1.67
    ķ
    -1.63
    ¿½
    -1.61
     contrast
    -1.59
    contrast
    -1.49
    ĸ´
    -1.49
    wing
    -1.48
     fear
    -1.45
     Th
    -1.44
     sick
    -1.42
    POSITIVE LOGITS
    liga
    1.97
    :`
    1.77
    usiness
    1.77
    journal
    1.71
    etry
    1.65
    iewicz
    1.63
    bsd
    1.63
     accelerator
    1.62
    zilla
    1.60
    agner
    1.59
    Activations Density 1.583%

    No Known Activations