© 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. MLP Post
    9. 0-MLP-SM
    11. 30729
    Prev
    Next
    INDEX
    Explanations

    the occurrence of specific code constructs or definitions in programming-related text

    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
    155
    +0.11
    0.7%
    58
    +0.11
    0.6%
    489
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.11
    0.13
    438
    +0.11
    0.12
    56
    +0.11
    0.03
    Negative Logits
    anium
    -1.93
     affirmed
    -1.50
    )">
    -1.48
     respectively
    -1.45
     silence
    -1.41
     convenience
    -1.39
     opened
    -1.39
     closing
    -1.37
     closed
    -1.36
    )}$.
    -1.34
    POSITIVE LOGITS
    bugs
    1.78
    writing
    1.59
    Blo
    1.56
    skins
    1.53
    PES
    1.52
    writers
    1.50
    books
    1.49
    fonts
    1.48
    authors
    1.46
    writer
    1.45
    Activations Density 4.709%

    No Known Activations