© 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. 30419
    Prev
    Next
    INDEX
    Explanations

    terms related to law enforcement

    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
    156
    +0.14
    0.8%
    365
    +0.11
    0.6%
    115
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    331
    +0.14
    0.02
    13
    +0.11
    0.02
    180
    +0.11
    0.02
    Negative Logits
    ĥ½
    -2.08
    TRODUCTION
    -1.93
    >&
    -1.84
    woke
    -1.81
    ĨĴ
    -1.61
    imester
    -1.54
    jours
    -1.51
    ussi
    -1.50
     transgender
    -1.50
     gay
    -1.49
    POSITIVE LOGITS
    craft
    1.86
     positions
    1.76
     tends
    1.69
     mechanism
    1.68
     relies
    1.63
     area
    1.63
     recognizes
    1.58
    ically
    1.58
     varies
    1.57
     oriented
    1.57
    Activations Density 0.173%

    No Known Activations