© 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. 29565
    Prev
    Next
    INDEX
    Explanations

    the Boolean value "False" across various contexts in programming documentation

    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
    488
    +0.14
    0.8%
    454
    +0.13
    0.7%
    326
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    488
    +0.14
    0.02
    82
    +0.13
    0.02
    454
    +0.12
    0.02
    Negative Logits
    las
    -1.73
     weight
    -1.46
    omet
    -1.45
    ween
    -1.39
    IT
    -1.38
     diameter
    -1.38
     nearer
    -1.37
    ONS
    -1.37
     fluid
    -1.35
     volumes
    -1.33
    POSITIVE LOGITS
    erals
    2.01
    ense
    1.77
    enstein
    1.56
    ña
    1.44
     means
    1.39
    enix
    1.39
    eland
    1.38
     copyrighted
    1.38
    ensa
    1.37
    eville
    1.35
    Activations Density 0.013%

    No Known Activations