© 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. 28265
    Prev
    Next
    INDEX
    Explanations

    articles indicating singularity or plurality

    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
    98
    +0.22
    1.2%
    478
    +0.20
    1.1%
    23
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    230
    +0.22
    0.03
    98
    +0.20
    0.00
    87
    +0.13
    0.02
    Negative Logits
    ®
    -3.81
    ¦
    -3.54
    ļ
    -3.46
    Ļª
    -3.45
    Ļ
    -3.40
    ¢
    -3.34
    IJ
    -3.25
    -3.23
    ↵
    -3.23
    č↵
    -3.23
    POSITIVE LOGITS
     certain
    1.86
     harmless
    1.79
     lot
    1.76
     *
    1.75
     much
    1.73
     valuable
    1.72
     reasonable
    1.72
     plethora
    1.67
     GNU
    1.66
     few
    1.65
    Activations Density 0.129%

    No Known Activations