© 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. 28663
    Prev
    Next
    INDEX
    Explanations

    the concept of mulching and its various applications in gardening and landscaping

    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
    111
    +0.12
    0.7%
    2
    +0.12
    0.7%
    318
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    240
    +0.12
    0.01
    451
    +0.12
    0.01
    202
    +0.12
    0.01
    Negative Logits
    ¯
    -2.25
    ľĵ
    -2.16
    ĥ
    -2.14
    Ĥ¬
    -1.91
    ĸ´
    -1.87
    »¿
    -1.83
    ĨĴ
    -1.80
    à±ģ
    -1.80
    ´
    -1.80
    ľ
    -1.73
    POSITIVE LOGITS
    ceral
    2.11
    stown
    1.81
    hold
    1.71
    hoe
    1.64
    het
    1.62
    ikel
    1.60
    lein
    1.57
     aside
    1.55
     recalls
    1.54
    cribed
    1.52
    Activations Density 0.006%

    No Known Activations