© 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 EvalsExportsAPI 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. 13421
    Prev
    Next
    INDEX
    Explanations

    code block structures and syntax elements within programming code

    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
    1.4%
    21
    +0.21
    1.2%
    23
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    191
    +0.23
    0.02
    157
    +0.21
    0.02
    57
    +0.11
    0.02
    Negative Logits
    ¿½
    -2.22
    »¿
    -1.92
    -1.69
    -1.69
    -1.69
    ↵
    -1.69
    -1.69
    -1.69
    ↵↵
    -1.69
     ↵
    -1.69
    POSITIVE LOGITS
     async
    1.61
    ween
    1.38
     from
    1.37
     React
    1.35
     //
    1.35
    `,
    1.34
    lements
    1.32
    athing
    1.32
     override
    1.31
     à²
    1.30
    Activations Density 0.064%

    No Known Activations