© 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. 30751
    Prev
    Next
    INDEX
    Explanations

    references to the act of reciting or repetition

    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
    +0.18
    1.0%
    125
    +0.16
    0.9%
    299
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    125
    +0.18
    0.03
    299
    +0.16
    0.02
    163
    +0.13
    0.02
    Negative Logits
    paces
    -1.69
     Consortium
    -1.61
    lands
    -1.60
    STER
    -1.54
    creas
    -1.44
    eln
    -1.40
    bras
    -1.39
    forth
    -1.34
    tern
    -1.33
     dire
    -1.33
    POSITIVE LOGITS
    ision
    1.69
    herche
    1.69
    ató
    1.65
    iative
    1.56
    oge
    1.55
    ycle
    1.54
    ryl
    1.50
    ceeding
    1.49
     wrong
    1.48
    ocious
    1.47
    Activations Density 0.037%

    No Known Activations