© 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. MLP Post
    9. 0-MLP-SM
    11. 28869
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "Rails" and its variants in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    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
    63
    +0.11
    0.6%
    146
    +0.11
    0.6%
    71
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    429
    +0.11
    0.01
    67
    +0.11
    0.01
    506
    +0.10
    0.01
    Negative Logits
     Os
    -1.57
    ras
    -1.52
    akin
    -1.51
    woke
    -1.48
     Salem
    -1.44
    arcer
    -1.38
     Labor
    -1.37
    irs
    -1.36
     Statistical
    -1.35
     GNU
    -1.35
    POSITIVE LOGITS
    finder
    1.85
    mith
    1.82
    ford
    1.80
    craft
    1.79
    cript
    1.77
    keeper
    1.75
    yard
    1.71
    erve
    1.71
    yards
    1.70
    antry
    1.67
    Activations Density 0.007%

    No Known Activations