© 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. 28302
    Prev
    Next
    INDEX
    Explanations

    non-spoken, indicative phrases or quotations

    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
    100
    +0.15
    0.9%
    250
    +0.12
    0.7%
    502
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.15
    0.22
    271
    +0.12
    0.09
    156
    +0.11
    0.11
    Negative Logits
     much
    -1.82
    ctrine
    -1.69
    hes
    -1.69
     least
    -1.63
    iousness
    -1.62
    iving
    -1.61
    omat
    -1.61
     architecture
    -1.58
    ivities
    -1.57
     grade
    -1.54
    POSITIVE LOGITS
    ĭ
    1.72
    ¼
    1.72
    fully
    1.71
    SESSION
    1.70
    Ķ
    1.70
    ĸ
    1.63
    Ĭ
    1.60
    #,
    1.60
    ¢
    1.60
    kubuntu
    1.59
    Activations Density 0.630%

    No Known Activations