© 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. 1-RES-SM
    11. 27584
    Prev
    Next
    INDEX
    Explanations

    code-related terms and syntax elements specific to programming 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/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
    44
    +0.13
    0.7%
    289
    +0.12
    0.7%
    271
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    273
    +0.13
    0.01
    460
    +0.12
    0.02
    329
    +0.10
    0.02
    Negative Logits
     boundaries
    -1.72
     Pradesh
    -1.70
    uler
    -1.65
     mark
    -1.59
    ¾
    -1.56
    ancer
    -1.56
     estate
    -1.55
     (%)
    -1.55
     deadline
    -1.54
    ½
    -1.54
    POSITIVE LOGITS
    obbsee
    1.58
    à°¿
    1.54
    rVert
    1.42
    Ñİ
    1.39
    ÑĹ
    1.38
     *
    1.36
    zitter
    1.35
    ãģĪ
    1.35
     clar
    1.34
    Ñħод
    1.33
    Activations Density 0.156%

    No Known Activations