© 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. 30402
    Prev
    Next
    INDEX
    Explanations

    the word "asting" and its variants

    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
    125
    +0.11
    0.6%
    249
    +0.10
    0.6%
    115
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.11
    0.01
    125
    +0.10
    0.01
    277
    +0.10
    0.01
    Negative Logits
    >'
    -1.61
     '</
    -1.54
    ...'
    -1.54
    '))
    -1.54
    .',
    -1.50
     (**
    -1.49
    CLA
    -1.49
    akin
    -1.49
    rosse
    -1.49
    obi
    -1.44
    POSITIVE LOGITS
    gres
    1.87
    ftware
    1.78
    facts
    1.65
    enstein
    1.65
    furt
    1.62
    ulated
    1.62
    holm
    1.57
    ist
    1.55
    emption
    1.54
    cule
    1.52
    Activations Density 0.011%

    No Known Activations