© 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. 26767
    Prev
    Next
    INDEX
    Explanations

    elements and structures related to programming or code documentation

    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
    91
    +0.13
    0.7%
    44
    +0.13
    0.7%
    296
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    296
    +0.13
    0.19
    91
    +0.13
    0.14
    75
    +0.12
    0.13
    Negative Logits
    etin
    -1.64
    amar
    -1.51
    openh
    -1.47
    itness
    -1.36
    edo
    -1.34
    cht
    -1.33
    aud
    -1.33
    idin
    -1.29
    aus
    -1.29
    atin
    -1.27
    POSITIVE LOGITS
     "</
    1.49
    ++)
    1.49
    unct
    1.41
    $.[]{
    1.40
    ourier
    1.36
     participant
    1.33
     sibling
    1.29
     pickup
    1.29
     placeholder
    1.28
    fileID
    1.28
    Activations Density 6.000%

    No Known Activations