© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2-MLP-SM
    11. 27090
    Prev
    Next
    INDEX
    Explanations

    references to police and law enforcement activities

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    392
    +0.12
    0.7%
    170
    +0.11
    0.6%
    68
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    68
    +0.12
    0.02
    162
    +0.11
    0.04
    392
    +0.11
    0.03
    Negative Logits
    »
    -2.01
    ½
    -1.76
    ¼
    -1.73
    Ł
    -1.72
    ively
    -1.61
    edo
    -1.61
    osti
    -1.55
    ŀ
    -1.53
    ª
    -1.53
    ¹
    -1.50
    POSITIVE LOGITS
     '{
    1.61
     ")
    1.58
    future
    1.55
    )",
    1.52
     electorate
    1.51
    velopment
    1.50
    wig
    1.49
    rangle
    1.46
     ')
    1.46
     ",
    1.44
    Activations Density 0.449%

    No Known Activations