© 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. 14367
    Prev
    Next
    INDEX
    Explanations

    instances of code or programming constructs related to configuration and data management

    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
    156
    +0.56
    4.2%
    111
    +0.42
    3.2%
    271
    +0.17
    1.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.56
    0.76
    156
    +0.42
    0.53
    71
    +0.17
    0.54
    Negative Logits
    č↵
    -2.79
    ↵↵
    -2.79
    -2.79
    ↵  ³³³
    -2.79
    <|outofrange|>
    -2.79
    -2.79
     ↵
    -2.79
    ↵
    -2.79
    č↵
    -2.79
    -2.79
    POSITIVE LOGITS
    amsbsy
    1.91
    amsmath
    1.71
    wasysym
    1.66
    mathrsfs
    1.64
    upgreek
    1.56
    amssymb
    1.52
    amsfonts
    1.48
    aligned
    1.31
    rosis
    1.21
    eq
    1.16
    Activations Density 0.854%

    No Known Activations