© 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. 25981
    Prev
    Next
    INDEX
    Explanations

    phrases related to same-sex attraction and relationships

    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
    1
    +0.11
    0.6%
    111
    +0.11
    0.6%
    293
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    293
    +0.11
    0.01
    1
    +0.11
    0.01
    34
    +0.10
    0.01
    Negative Logits
     ')
    -1.80
     awake
    -1.75
    hores
    -1.73
     complete
    -1.69
     sudden
    -1.69
     mornings
    -1.58
    cause
    -1.57
     '</
    -1.55
     wisdom
    -1.55
     full
    -1.55
    POSITIVE LOGITS
    "}](#
    1.89
    burg
    1.89
    cript
    1.80
    esan
    1.79
    sheet
    1.78
    olver
    1.78
    uality
    1.75
    mary
    1.75
    cribed
    1.73
    iewicz
    1.68
    Activations Density 0.013%

    No Known Activations