© 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. 2-RES-SM
    11. 12958
    Prev
    Next
    INDEX
    Explanations

    references to America and 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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    130
    +0.14
    0.8%
    156
    +0.13
    0.7%
    457
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    250
    +0.14
    0.04
    421
    +0.13
    0.02
    413
    +0.12
    0.01
    Negative Logits
    ĻĤ
    -2.41
    ij
    -2.14
    ¿
    -2.08
    IJ
    -1.97
    ±
    -1.88
    İ
    -1.87
    ¼
    -1.84
    µ
    -1.82
    ¾
    -1.82
    ĥ½
    -1.81
    POSITIVE LOGITS
     Airlines
    1.92
    ICO
    1.84
    arium
    1.61
    's
    1.57
     Rising
    1.55
    qua
    1.55
     Today
    1.49
     centr
    1.45
    ward
    1.44
     Yard
    1.43
    Activations Density 0.198%

    No Known Activations