© 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. 27989
    Prev
    Next
    INDEX
    Explanations

    instances of the word "oc," indicating a focus on a specific type of content or topic related to that term

    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
    79
    +0.12
    0.7%
    410
    +0.12
    0.7%
    343
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    445
    +0.12
    0.02
    79
    +0.12
    0.02
    35
    +0.10
    0.01
    Negative Logits
    FPar
    -1.59
     sudden
    -1.43
     certain
    -1.43
    ware
    -1.38
     overtime
    -1.32
    unreadable
    -1.30
    OTHER
    -1.27
    future
    -1.26
     quo
    -1.26
     two
    -1.23
    POSITIVE LOGITS
    ij
    1.90
    entric
    1.88
    het
    1.85
    Īĺ
    1.81
    hel
    1.70
    idad
    1.70
     view
    1.68
    ución
    1.64
    IJ
    1.62
    ¢
    1.61
    Activations Density 0.067%

    No Known Activations