© 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. 26613
    Prev
    Next
    INDEX
    Explanations

    references to anatomical or physiological structures in a medical context

    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
    321
    +0.15
    0.9%
    256
    +0.13
    0.7%
    362
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.15
    0.01
    32
    +0.13
    0.01
    405
    +0.12
    0.01
    Negative Logits
    ever
    -1.63
    ting
    -1.52
     potential
    -1.43
     happening
    -1.43
    AVE
    -1.43
     otherwise
    -1.39
    cher
    -1.37
     then
    -1.31
    here
    -1.30
    arer
    -1.30
    POSITIVE LOGITS
    "}](#
    1.89
    iors
    1.86
    ±
    1.77
    Ģ
    1.72
    àµį
    1.70
    áĢ¬
    1.68
    ģ
    1.67
    à«ĩ
    1.67
    áŁ
    1.63
    ி
    1.61
    Activations Density 0.405%

    No Known Activations