© 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. 29102
    Prev
    Next
    INDEX
    Explanations

    terms related to complications or negative outcomes associated with various subjects

    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
    177
    +0.14
    0.8%
    376
    +0.12
    0.7%
    365
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    177
    +0.14
    0.01
    15
    +0.12
    0.01
    453
    +0.10
    0.01
    Negative Logits
    ¿½
    -2.36
    ĥ½
    -2.08
    ¿
    -1.97
    rely
    -1.94
    lick
    -1.72
     spent
    -1.64
    xit
    -1.62
    ²
    -1.62
     kindly
    -1.61
    LLOW
    -1.58
    POSITIVE LOGITS
    "}](#
    2.13
    circuit
    1.89
    arial
    1.86
    bolt
    1.74
    cav
    1.74
     lanes
    1.70
    uary
    1.65
    stown
    1.63
    izes
    1.63
    ior
    1.61
    Activations Density 0.011%

    No Known Activations