© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 26990
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the abbreviation "ms."

    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
    +0.13
    0.8%
    286
    +0.11
    0.7%
    467
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    4
    +0.13
    0.02
    286
    +0.11
    0.02
    15
    +0.10
    0.02
    Negative Logits
    YING
    -1.92
    ISHED
    -1.75
    aning
    -1.73
    ANE
    -1.60
    ying
    -1.60
    obbsee
    -1.59
    ms
    -1.59
    inating
    -1.53
    ATION
    -1.52
    aped
    -1.50
    POSITIVE LOGITS
    boro
    1.88
    iewicz
    1.77
    heet
    1.74
    leys
    1.69
    ley
    1.67
    chip
    1.64
    chaft
    1.62
    hurst
    1.62
    ician
    1.59
    port
    1.58
    Activations Density 0.545%

    No Known Activations