© 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. 2-MLP-SM
    11. 23124
    Prev
    Next
    INDEX
    Explanations

    phrases that express issues or problems related to various subjects

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    403
    +0.14
    0.8%
    170
    +0.13
    0.7%
    243
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    407
    +0.14
    0.09
    362
    +0.13
    0.06
    404
    +0.12
    0.08
    Negative Logits
    ¬
    -2.10
    ¤
    -1.92
    ¥
    -1.90
    Ń
    -1.81
    ²
    -1.77
    ĻĤ
    -1.68
    §
    -1.68
    Ĭ
    -1.67
    ¨
    -1.64
    ij
    -1.61
    POSITIVE LOGITS
    $.[]{
    1.62
     alone
    1.62
    ’.
    1.61
    ()).
    1.50
     Wales
    1.49
    rsquo
    1.43
    ês
    1.42
    .[]{
    1.41
    npmjs
    1.41
    zos
    1.40
    Activations Density 0.664%

    No Known Activations