© 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. 4-RES-SM
    11. 14421
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to data structures and their manipulation

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    78
    +0.23
    1.3%
    21
    +0.14
    0.8%
    280
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    27
    +0.23
    0.04
    78
    +0.14
    0.01
    255
    +0.12
    0.00
    Negative Logits
    -2.06
    ↵
    -2.06
    -2.06
    -2.06
    -2.06
    ↵↵
    -2.06
    -2.06
    -2.06
    ↵
    -2.06
    ↵
    -2.06
    POSITIVE LOGITS
    ++){
    2.73
    ++)
    2.64
    ++
    2.17
    ++,
    2.04
     ++
    1.97
    __)
    1.70
    ){
    1.69
    _)
    1.68
     ){
    1.66
    <=
    1.63
    Activations Density 0.173%

    No Known Activations