© 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. 24389
    Prev
    Next
    INDEX
    Explanations

    references to web links and related elements

    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
    365
    +0.12
    0.7%
    181
    +0.11
    0.6%
    221
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.12
    0.09
    129
    +0.11
    0.01
    365
    +0.11
    0.04
    Negative Logits
     (%)
    -1.66
    ophyll
    -1.64
     intervals
    -1.60
     Adjust
    -1.58
    nez
    -1.57
     pad
    -1.52
     adjust
    -1.50
     calculate
    -1.50
     Measurements
    -1.50
    ifice
    -1.49
    POSITIVE LOGITS
    ŀ
    2.21
    ĵ
    2.16
    ¿½
    1.95
    ĥ½
    1.91
    į
    1.85
    ĨĴ
    1.84
    ¾
    1.73
    ©
    1.72
    ª
    1.69
    Ļª
    1.68
    Activations Density 0.625%

    No Known Activations