© 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. 25446
    Prev
    Next
    INDEX
    Explanations

    specific formatting or encoding markers within 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
    474
    +0.13
    0.8%
    258
    +0.13
    0.8%
    322
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    474
    +0.13
    0.01
    322
    +0.13
    0.01
    435
    +0.11
    0.01
    Negative Logits
    Ń
    -1.87
    ¬
    -1.79
    ¶
    -1.63
     meantime
    -1.62
    Ĥ
    -1.60
    ľ
    -1.60
     shown
    -1.53
    quired
    -1.53
    oning
    -1.51
     prelim
    -1.49
    POSITIVE LOGITS
    ://
    1.87
    pieces
    1.81
    points
    1.65
    isti
    1.65
    uitar
    1.63
    arts
    1.63
    rives
    1.62
    fires
    1.60
    gmail
    1.59
    liga
    1.57
    Activations Density 0.059%

    No Known Activations