© 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. 25495
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and formatting symbols

    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
    23
    +0.26
    1.5%
    478
    +0.23
    1.3%
    217
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    217
    +0.26
    0.03
    16
    +0.23
    0.03
    180
    +0.13
    0.02
    Negative Logits
    ista
    -1.81
    icago
    -1.79
    iper
    -1.78
     Rptr
    -1.75
    -
    -1.72
    fecture
    -1.70
    itat
    -1.70
    atas
    -1.65
    "}](#
    -1.64
    bp
    -1.62
    POSITIVE LOGITS
     \'
    1.82
     âĢŀ
    1.67
     latter
    1.60
    ĸ´
    1.55
     ''
    1.53
    leans
    1.53
     obese
    1.52
     ‘
    1.51
     blame
    1.49
     lack
    1.48
    Activations Density 0.116%

    No Known Activations