© 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. 28081
    Prev
    Next
    INDEX
    Explanations

    expressions of sympathy and compassion towards individuals or situations

    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
    +0.20
    1.2%
    376
    +0.18
    1.0%
    256
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    266
    +0.20
    0.01
    200
    +0.18
    0.01
    156
    +0.12
    0.01
    Negative Logits
    auc
    -1.67
    eks
    -1.50
     brutal
    -1.45
    urer
    -1.43
    uring
    -1.41
    asta
    -1.36
    urers
    -1.36
    ssä
    -1.34
    ção
    -1.33
    ylase
    -1.32
    POSITIVE LOGITS
    ¢
    1.79
    din
    1.64
     direction
    1.58
     towards
    1.53
    sci
    1.52
     duties
    1.47
     directions
    1.45
    gery
    1.44
    ¨
    1.43
     toward
    1.43
    Activations Density 0.019%

    No Known Activations