© 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. 29978
    Prev
    Next
    INDEX
    Explanations

    the repeated instance of a specific token

    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
    410
    +0.14
    0.8%
    441
    +0.11
    0.6%
    34
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.14
    0.01
    295
    +0.11
    0.01
    434
    +0.11
    0.01
    Negative Logits
    est
    -1.62
    ests
    -1.44
     etc
    -1.41
    Âł↵
    -1.39
     invention
    -1.39
     xe
    -1.37
     xcex
    -1.34
     gradient
    -1.33
     said
    -1.33
     streams
    -1.33
    POSITIVE LOGITS
    ī
    2.32
    ½
    2.27
    ↵
    2.26
     ↵
    2.26
    <|padding|>
    2.26
    č↵
    2.26
    č↵
    2.26
    ↵
    2.26
    2.26
    ↵
    2.26
    Activations Density 1.641%

    No Known Activations