© 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. 29883
    Prev
    Next
    INDEX
    Explanations

    mentions of radiographs

    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
    +0.17
    1.0%
    352
    +0.11
    0.6%
    19
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    292
    +0.17
    0.38
    310
    +0.11
    0.31
    160
    +0.11
    0.29
    Negative Logits
    )){
    -1.73
     conscience
    -1.71
    cibly
    -1.68
     sudden
    -1.67
     certain
    -1.67
    ubicin
    -1.67
     APPEALS
    -1.64
     loneliness
    -1.54
     particular
    -1.52
     lonely
    -1.50
    POSITIVE LOGITS
    ist
    2.07
    heet
    1.97
    Bank
    1.87
    helf
    1.85
    heets
    1.78
    ios
    1.77
    ista
    1.77
    icle
    1.75
    bank
    1.71
    picture
    1.70
    Activations Density 0.923%

    No Known Activations