© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 25238
    Prev
    Next
    INDEX
    Explanations

    instances of the word "concussion."

    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
    376
    +0.16
    0.9%
    111
    +0.15
    0.8%
    354
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.16
    0.01
    194
    +0.15
    0.01
    465
    +0.12
    0.01
    Negative Logits
    emente
    -1.67
    mes
    -1.64
    |$.
    -1.59
    nez
    -1.57
    flies
    -1.57
    resa
    -1.53
    hood
    -1.53
    empre
    -1.51
    mente
    -1.49
    ÑĤÑĮ
    -1.44
    POSITIVE LOGITS
     compared
    1.63
    isely
    1.61
    ussion
    1.44
    iative
    1.44
    idone
    1.41
    elled
    1.40
     tolerance
    1.38
     measure
    1.38
     conceded
    1.37
    ussions
    1.36
    Activations Density 0.012%

    No Known Activations