© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 14100
    Prev
    Next
    INDEX
    Explanations

    structural elements in programming or markup languages

    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
    17
    +0.17
    1.0%
    73
    +0.14
    0.8%
    419
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    371
    +0.17
    0.06
    192
    +0.14
    0.04
    107
    +0.11
    0.04
    Negative Logits
    agna
    -1.61
    exe
    -1.50
    shift
    -1.45
    .^\[[@
    -1.40
    dll
    -1.35
    áĢ¬
    -1.33
    iNdEx
    -1.29
    orta
    -1.29
    .<
    -1.28
    si
    -1.27
    POSITIVE LOGITS
    ĥ½
    3.07
    ·¸
    2.66
    ↵
    2.58
    ↵
    2.58
    ↵        ↵
    2.58
    ↵
    2.58
    ↵
    2.58
    2.58
    ↵↵↵
    2.58
    č↵
    2.58
    Activations Density 0.783%

    No Known Activations