© 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. 25740
    Prev
    Next
    INDEX
    Explanations

    terms related to binary formats and distributions in software licensing

    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
    507
    +0.13
    0.7%
    139
    +0.13
    0.7%
    289
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    139
    +0.13
    0.02
    298
    +0.13
    0.02
    289
    +0.12
    0.01
    Negative Logits
    begin
    -1.72
    allow
    -1.68
    ³
    -1.59
    leading
    -1.56
    оз
    -1.53
     my
    -1.51
    ocratic
    -1.50
    friend
    -1.45
    ¸
    -1.45
    jee
    -1.45
    POSITIVE LOGITS
     Laden
    1.95
    sburg
    1.82
     filings
    1.66
    iza
    1.63
    sworth
    1.60
    taire
    1.50
    stown
    1.50
    tek
    1.49
    beans
    1.46
    terness
    1.45
    Activations Density 0.059%

    No Known Activations