© 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. 29537
    Prev
    Next
    INDEX
    Explanations

    the term "zeolite" in various contexts related to catalysts

    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
    369
    +0.16
    0.9%
    376
    +0.16
    0.9%
    22
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    22
    +0.16
    0.01
    44
    +0.16
    0.01
    491
    +0.14
    0.01
    Negative Logits
     thereof
    -1.60
    sis
    -1.48
     commission
    -1.45
     said
    -1.44
    western
    -1.42
    s
    -1.42
     Association
    -1.38
     intention
    -1.35
     Description
    -1.33
     dozen
    -1.32
    POSITIVE LOGITS
    alous
    2.26
    ilee
    1.88
    ÅĽ
    1.86
    pto
    1.79
    ÅĨ
    1.77
    ppo
    1.74
    ños
    1.70
    eto
    1.68
    ño
    1.65
     yourselves
    1.62
    Activations Density 0.232%

    No Known Activations