© 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. 28510
    Prev
    Next
    INDEX
    Explanations

    references to specific names, including brands, products, and notable individuals

    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
    412
    +0.14
    0.8%
    369
    +0.13
    0.7%
    319
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    412
    +0.14
    0.01
    71
    +0.13
    0.01
    319
    +0.12
    0.01
    Negative Logits
    yz
    -1.90
     someone
    -1.63
     somebody
    -1.59
     anybody
    -1.54
    elo
    -1.51
     anyone
    -1.48
     vista
    -1.40
     dad
    -1.39
    yx
    -1.39
     nada
    -1.38
    POSITIVE LOGITS
    arman
    1.77
    issance
    1.61
    obe
    1.61
    istani
    1.58
    oon
    1.52
    estone
    1.47
    inese
    1.43
    inth
    1.40
    ieux
    1.40
     (),
    1.37
    Activations Density 0.015%

    No Known Activations