© 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 EvalsExportsAPI 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. 28583
    Prev
    Next
    INDEX
    Explanations

    verbs related to examination and exploration of topics

    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
    23
    +0.15
    0.8%
    266
    +0.13
    0.7%
    115
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    345
    +0.15
    0.02
    316
    +0.13
    0.01
    266
    +0.13
    0.01
    Negative Logits
    ensen
    -1.82
    's
    -1.70
    imab
    -1.68
    ened
    -1.59
    neys
    -1.57
    ball
    -1.54
    genstein
    -1.50
     editions
    -1.46
     mentions
    -1.46
    enson
    -1.44
    POSITIVE LOGITS
    hift
    2.01
    hin
    1.76
     backward
    1.73
    hip
    1.70
    ĻĤ
    1.70
    ldots
    1.62
    uppose
    1.52
    dots
    1.47
    omething
    1.45
     how
    1.43
    Activations Density 0.023%

    No Known Activations