© 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. 25923
    Prev
    Next
    INDEX
    Explanations

    references to specific subjects or items being discussed in the 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
    372
    +0.14
    0.8%
    199
    +0.12
    0.7%
    226
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    402
    +0.14
    0.15
    26
    +0.12
    0.14
    199
    +0.11
    0.14
    Negative Logits
    ipore
    -1.60
    iles
    -1.52
    riz
    -1.48
    rika
    -1.43
    rocy
    -1.43
    scar
    -1.42
     refractory
    -1.41
     critically
    -1.39
     pharmacokinetic
    -1.39
    cember
    -1.38
    POSITIVE LOGITS
    ={
    1.84
     else
    1.84
    '$
    1.71
    '>
    1.71
    >"
    1.69
    ‘
    1.69
    instance
    1.67
    `
    1.64
    {{
    1.62
    [_
    1.62
    Activations Density 0.272%

    No Known Activations