© 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. 28684
    Prev
    Next
    INDEX
    Explanations

    repeated occurrences of the word "they."

    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
    358
    +0.14
    0.8%
    17
    +0.12
    0.7%
    135
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    74
    +0.14
    0.12
    352
    +0.12
    0.11
    143
    +0.10
    0.09
    Negative Logits
     mandate
    -1.44
    SHIFT
    -1.32
     retin
    -1.32
    Shift
    -1.31
     theta
    -1.30
     BCG
    -1.28
     LAP
    -1.27
     NIH
    -1.23
     electrodes
    -1.22
    around
    -1.22
    POSITIVE LOGITS
    writer
    2.17
    writing
    1.97
    alling
    1.82
    alls
    1.72
    olas
    1.71
    alled
    1.69
    writers
    1.66
    hline
    1.65
    aho
    1.64
    riend
    1.50
    Activations Density 0.144%

    No Known Activations