© 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. 26571
    Prev
    Next
    INDEX
    Explanations

    instances of the word "and" as well as phrases indicating a conjunction or connection between concepts

    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
    390
    +0.15
    0.8%
    182
    +0.13
    0.7%
    194
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    494
    +0.15
    0.45
    209
    +0.13
    0.28
    402
    +0.11
    0.25
    Negative Logits
    >[
    -1.62
    enza
    -1.59
    asek
    -1.57
    encia
    -1.48
    ?).
    -1.47
    ?)
    -1.47
    erm
    -1.43
    essen
    -1.43
    emen
    -1.42
    >
    -1.39
    POSITIVE LOGITS
    ĥ½
    4.37
    ľ
    4.14
    ³
    4.04
    Ļª
    4.03
    ĥ
    4.00
    ľĵ
    3.99
    ²
    3.90
    ¬
    3.82
    ķ
    3.82
    Ľ
    3.77
    Activations Density 1.987%

    No Known Activations