© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 22523
    Prev
    Next
    INDEX
    Explanations

    words related to intimate or sexual activities

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.14
    0.8%
    475
    +0.12
    0.7%
    135
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    475
    +0.14
    0.03
    42
    +0.12
    0.04
    491
    +0.11
    0.02
    Negative Logits
     possession
    -1.57
     Borough
    -1.57
    Bey
    -1.38
     competitive
    -1.38
     arsenal
    -1.37
    framework
    -1.37
     appreciation
    -1.35
    naissance
    -1.31
     Guard
    -1.28
     anthem
    -1.28
    POSITIVE LOGITS
    ±
    1.90
    ¯
    1.80
    ij
    1.79
    itations
    1.65
    §
    1.60
    ivated
    1.59
    ailed
    1.56
    ib
    1.55
    «
    1.54
     _(
    1.51
    Activations Density 0.441%

    No Known Activations