© 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. 29060
    Prev
    Next
    INDEX
    Explanations

    measurements or quantities related to weight and health

    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
    350
    +0.16
    0.9%
    87
    +0.14
    0.8%
    111
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.16
    0.02
    321
    +0.14
    0.01
    271
    +0.12
    0.00
    Negative Logits
    <|outofrange|>
    -3.69
    <|outofrange|>
    -3.69
    -3.69
     ↵
    -3.69
    -3.69
    ↵↵
    -3.69
    -3.69
    -3.69
    ↵
    -3.69
    -3.69
    POSITIVE LOGITS
    erals
    1.84
    ération
    1.68
    hift
    1.64
    ipel
    1.64
    dess
    1.62
    lications
    1.61
    ksen
    1.58
    .,
    1.57
    enic
    1.54
    esan
    1.53
    Activations Density 0.013%

    No Known Activations