© 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. 25966
    Prev
    Next
    INDEX
    Explanations

    topics related to medical errors and their impact on healthcare

    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
    272
    +0.12
    0.7%
    118
    +0.12
    0.6%
    146
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    438
    +0.12
    0.39
    53
    +0.12
    0.42
    56
    +0.12
    0.11
    Negative Logits
    _**
    -1.48
    ).)
    -1.48
     HL
    -1.45
     why
    -1.44
    )\].
    -1.41
    pling
    -1.37
    )"
    -1.33
    ubottu
    -1.32
    äng
    -1.31
    bral
    -1.31
    POSITIVE LOGITS
    mente
    1.72
    mas
    1.68
    ocene
    1.64
    orems
    1.62
    ists
    1.59
    ’
    1.52
     (“
    1.51
    matically
    1.50
    onset
    1.47
    ctomy
    1.47
    Activations Density 4.627%

    No Known Activations