© 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. 13364
    Prev
    Next
    INDEX
    Explanations

    instances of specific characters or symbols used in programming syntax

    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
    67
    +0.18
    1.0%
    372
    +0.13
    0.7%
    342
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    67
    +0.18
    0.02
    129
    +0.13
    0.01
    342
    +0.13
    0.04
    Negative Logits
    oute
    -1.42
     Sus
    -1.39
    iary
    -1.32
    empt
    -1.32
     Peru
    -1.31
     Pet
    -1.29
    icular
    -1.29
     Malaysia
    -1.25
    aday
    -1.24
    shire
    -1.23
    POSITIVE LOGITS
     G
    4.12
    G
    3.69
     g
    3.43
    g
    3.27
    Gs
    3.21
    ĻĤ
    3.07
    GS
    2.93
    GN
    2.90
    GD
    2.88
     GS
    2.87
    Activations Density 1.843%

    No Known Activations