© 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. 26531
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "operation"

    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
    441
    +0.11
    0.6%
    266
    +0.11
    0.6%
    256
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.11
    0.02
    266
    +0.11
    0.02
    152
    +0.10
    0.02
    Negative Logits
    jar
    -1.55
    owing
    -1.49
     ransom
    -1.42
     blame
    -1.39
     prayer
    -1.36
    ######
    -1.36
    \)
    -1.36
    )$)
    -1.34
     possess
    -1.34
     inward
    -1.30
    POSITIVE LOGITS
    imetry
    1.79
    acks
    1.75
    atives
    1.66
    iah
    1.62
    ives
    1.56
    acional
    1.53
    ford
    1.53
    nan
    1.52
    istor
    1.52
    ats
    1.52
    Activations Density 0.093%

    No Known Activations