© 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 EvalsExportsAPI 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. 28454
    Prev
    Next
    INDEX
    Explanations

    references to wisdom and prudent decision-making

    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
    376
    +0.18
    1.0%
    219
    +0.12
    0.7%
    78
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.18
    0.02
    432
    +0.12
    0.01
    288
    +0.12
    0.01
    Negative Logits
     altogether
    -1.99
    ation
    -1.68
    istence
    -1.58
    abel
    -1.57
    :</
    -1.49
    ulos
    -1.47
    ivity
    -1.44
     laps
    -1.43
     entirely
    -1.42
     Islands
    -1.41
    POSITIVE LOGITS
    guy
    1.78
    ctor
    1.76
     theater
    1.62
    emente
    1.60
    guide
    1.59
    coin
    1.56
    ressive
    1.45
    indows
    1.44
    upgreek
    1.43
    kids
    1.42
    Activations Density 2.991%

    No Known Activations